Memory MCP Server

by michael-denyer

Overview Schema Related Servers Score Discussions

Python

Local

Server Quality Checklist

Profile completionA complete profile improves this server's visibility in search results.

Latest release: v0.8.0
Disambiguation3/5
There are multiple tools for similar purposes (e.g., recall, recall_by_tag, recall_with_fallback; find_contradictions, get_contradictions, mark_contradiction), but descriptions help differentiate them. Some overlap exists, especially among recall variants and validation/invalidation tools.
Naming Consistency3/5
Naming conventions are mixed: some use verb_noun (e.g., list_memories, link_memories), others are phrases or single verbs (e.g., remember, forget, hot_cache_status). While most are readable, the pattern is not uniform.
Tool Count2/5
56 tools is excessive for a single server. Many tools are specialized variants or internal utilities (e.g., db_info, metrics_status) that could be consolidated. The high number makes the tool surface hard to navigate.
Completeness4/5
The tool set covers the full lifecycle of memory management: storage, recall, validation, relationships, contradictions, hot cache, sessions, mining, consolidation, and maintenance. Only minor gaps exist (e.g., batch operations on memories could be more explicit).
Average 3.8/5 across 56 of 56 tools scored. Lowest: 2.7/5.
See the Tool Scores section below for per-tool breakdowns.
- No community issues in the last 6 months
- 26 commits in the last 12 weeks
- Last stable release on July 2, 2026
- No critical vulnerability alerts
- No high-severity vulnerability alerts
- No code scanning findings
- CI is passing
This repository is licensed under MIT License.
This repository includes a README.md file.
No tool usage detected in the last 30 days. Usage tracking helps demonstrate server value.
Tip: use the "Try in Browser" feature on the server page to seed initial usage.
Add a glama.json file to provide metadata about your server.
If you are the author, simply .
If the server belongs to an organization, first add glama.json to the root of your repository:
```
{
  "$schema": "https://glama.ai/mcp/schemas/server.json",
  "maintainers": [
    "your-github-username"
  ]
}
```
Then . Browse examples.
Add related servers to improve discoverability.

How to sync the server with GitHub?

Servers are automatically synced at least once per day, but you can also sync manually at any time to instantly update the server profile.

To manually sync the server, click the "Sync Server" button in the MCP server admin interface.

How is the quality score calculated?

The overall quality score combines two components: Tool Definition Quality (70%) and Server Coherence (30%).

Tool Definition Quality measures how well each tool describes itself to AI agents. Every tool is scored 1–5 across six dimensions: Purpose Clarity (25%), Usage Guidelines (20%), Behavioral Transparency (20%), Parameter Semantics (15%), Conciseness & Structure (10%), and Contextual Completeness (10%). The server-level definition quality score is calculated as 60% mean TDQS + 40% minimum TDQS, so a single poorly described tool pulls the score down.

Server Coherence evaluates how well the tools work together as a set, scoring four dimensions equally: Disambiguation (can agents tell tools apart?), Naming Consistency, Tool Count Appropriateness, and Completeness (are there gaps in the tool surface?).

Tiers are derived from the overall score: A (≥3.5), B (≥3.0), C (≥2.0), D (≥1.0), F (<1.0). B and above is considered passing.

Tool Scores

Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It fails to disclose any behavioral traits like read-only nature (likely), security requirements, or what 'details' entails.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is too minimal. While concise, it omits necessary details and does not fully earn its place as it lacks useful information beyond the tool name.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite an output schema existing (not shown), the description does not explain what the output contains or any operational context. For a simple retrieval tool, more context about 'details' would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the description adds no extra meaning beyond what the schema already provides for 'session_id'. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves details for a specific session, using a specific verb and resource. It is distinct from siblings like 'get_sessions' (plural) and 'end_session'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. It implies use when you have a session ID, but does not mention when not to use or compare to other tools like 'get_sessions'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits, but it only states 'list stored memories with pagination.' It does not mention read-only nature, default ordering, effect of parameters, or any side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, efficient and front-loaded. However, it could benefit from adding value without becoming verbose, hence not a 5.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the existence of an output schema and many sibling tools, the description lacks necessary context such as what constitutes a 'memory,' default sorting, and relationship to other listing/retrieval tools. Important gaps remain.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage with descriptions for each parameter. The description adds only 'with pagination,' which hints at limit/offset but adds no new meaning beyond the schema. This meets the baseline for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool 'list stored memories with pagination,' which combines a specific verb and resource. However, it does not distinguish itself from sibling tools like 'get_session_memories' or 'recall,' which also list or retrieve memories.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., recall, get_session_memories). There is no mention of context, exclusions, or specific scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. It merely states the tool logs output, without mentioning side effects, idempotency, permissions, or any constraints beyond the basic action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise at one sentence, front-loading the core purpose. While brief, it avoids waste; however, it could include more detail without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (2 parameters, no nesting) and the presence of an output schema, the description is incomplete. It lacks context on when manual invocation is appropriate and does not explain the output schema's role.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage with descriptions for both parameters (content and session_id). The description adds no additional meaning beyond the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool logs output for pattern mining, specifying a verb (log) and resource (output for pattern mining). It also notes it can be called automatically or manually. However, it does not fully distinguish from similar logging tools among siblings, though none are obvious.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description only mentions the tool can be called automatically or manually, providing no explicit guidance on when to use it versus alternative tools, nor any conditions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description only says 'Get statistics' but does not disclose any behavioral traits such as side effects, read-only nature, or what the statistics entail. With no annotations, the description fails to adequately inform the agent about the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no wasted words. It is concise and directly states the tool's purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's name 'relationship_stats' and siblings like 'memory_stats', the description is too brief. It does not specify what statistics are returned or how it differs from similar tools, making it incomplete for an effective tool selection.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has zero parameters, so schema coverage is 100%. The baseline is 4, but the description is vague about what 'statistics' means. An output schema exists, but the description does not add meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns statistics about memory relationships in the knowledge graph. However, it does not differentiate from sibling tools like 'memory_stats', which could be confused.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as 'memory_stats' or 'retrieval_quality_stats'. The context signals show many sibling tools, but the description offers no usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only mentions storing and returning an ID. It does not disclose persistence behavior, overwrite rules, or side effects of memory creation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise at two sentences, with no wasted words. However, it could benefit from more detail without sacrificing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 5 parameters, an output schema, and numerous sibling tools, the description is insufficient. It fails to explain memory organization (categories, tags) or how this tool fits into the memory management workflow.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% but the description adds no additional meaning beyond the schema. Baseline 3 is appropriate as the schema already documents parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Store a new memory' which is a specific verb and resource. It distinguishes from sibling tools like recall (retrieve) and forget (delete) but does not elaborate on memory types.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like list_memories or recall. There are no exclusions or context about prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description only states 'show', implying read-only but no details on side effects, performance, or data freshness. Minimal behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with the verb. Efficient but could add a bit more detail without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no parameters and an output schema, the description is minimally sufficient but lacks context on when statistics are available or what they represent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, so the baseline is 4. The description correctly indicates no input needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool shows pattern mining statistics, which is a specific verb+resource pair. However, it does not differentiate from similar sibling tools like memory_stats or metrics_status.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. There is no mention of prerequisites or context for interpretation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden. It conveys irreversibility via 'permanently', but lacks details on side effects, permissions, or behavior beyond deletion.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no waste. Could benefit from additional context without becoming verbose, but current conciseness is effective.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and an output schema, the description is adequate. However, more context about permanence and data relationships would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the description adds no extra meaning to the parameter. Baseline 3 is appropriate as it does not compensate for other gaps.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (delete) and resource (memory), adding 'permanently' for emphasis. It is specific but does not distinguish from sibling tool 'invalidate_memory'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, no when-not-to-use information, and no mention of prerequisites or consequences.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full responsibility. It mentions 'rejecting' and 'removing', implying a destructive action, but does not disclose whether the action is reversible, what permissions are required, or any side effects on related data.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single clear sentence with no wasted words. It is extremely concise, though it could benefit from slightly more detail without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and an output schema, the description covers the basic functionality. However, it lacks explanation of what 'reject' means in terms of state transitions and how it differs from other removal tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a single parameter 'pattern_id' described as 'ID of mined pattern to reject'. The description adds no additional meaning beyond the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Reject'), the resource ('a mined pattern'), and the effect ('removing it from candidates'). It distinguishes itself from siblings like 'approve_candidate' and 'bulk_reject_candidates' by specifying the individual rejection of a single pattern.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no usage guidance, such as when to use this tool instead of 'bulk_reject_candidates' or 'forget'. It lacks context on prerequisites, such as requiring the pattern to be in a 'candidate' state.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose that this is a read-only operation and any side effects. It only states 'get', which is presumed safe, but lacks explicit behavioral details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core purpose, and contains no extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
While there is an output schema, the description omits details like pagination or sorting behavior. The 'limit' parameter's effect is not explicitly stated, leaving some gaps for a simple retrieval tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the description adds no extra meaning beyond what the schema already provides for 'session_id' and 'limit'. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves memories from a specific session. While it doesn't explicitly differentiate from siblings like 'list_memories' or 'recall', the scope is precise.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
It suggests using the tool to explore learned information, which implies a read-only use case. However, it provides no guidance on when not to use it or alternatives among many memory-related siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description implies a read-only operation ('Get'), but without annotations, it does not explicitly state safety, idempotency, or other behavioral traits. It is minimally transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence, but it could be slightly more informative without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the existence of an output schema, the description does not need to detail return values, but it could still provide more context about what 'memory statistics' entails (e.g., memory usage, health indicators) to be fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, which according to the rubric sets a baseline of 4. No additional parameter information is needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The phrase 'Get memory statistics' clearly indicates retrieving statistics related to memory. However, it lacks specificity to differentiate from similar tools like 'metrics_status' or 'retrieval_quality_stats'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidance is provided. There is no mention of when to use this tool vs. alternatives, nor any prerequisites or side effects.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It describes that sessions track memories and that this tool returns recent sessions, but it lacks behavioral details such as whether it is read-only, if there is pagination, or any side effects. The existence of an output schema partially compensates, but the description itself is minimal on behavioral disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences long, with the primary action in the first sentence. It is concise, front-loaded, and every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a relatively simple tool with two optional parameters and an output schema, the description provides sufficient context: it explains what sessions are and how to use the tool. It could mention that it returns a list of sessions, but the output schema likely covers that. Overall, it feels complete enough for most use cases.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Both parameters (limit, project_path) have descriptions in the input schema (100% coverage), so the schema already documents them. The description does not add any additional parameter guidance, which meets the baseline expectation for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Get recent conversation sessions.' It also provides context on what sessions are. While it hints at navigation, it doesn't explicitly differentiate from siblings like get_session, so sibling distinction is somewhat implicit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description says 'Use this to see conversation history and navigate to specific sessions,' which provides basic usage guidance. However, it does not mention when not to use this tool or explicitly point to alternatives (e.g., get_session for a single session).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations; description lacks behavioral details like read-only nature, result order, or scope. Only states basic retrieval.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, very concise. Could add minimal context without losing efficiency.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for a simple tool with output schema, but leaves ambiguity about result format and differentiation from siblings.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
100% schema coverage; description adds no extra meaning beyond what parameters already declare.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clear verb 'Get' and resource 'memories' with filter 'with a specific tag'. Distinguishes from siblings like 'recall' which likely has no tag filter.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implied usage (when filtering by tag) but no explicit when-not or alternative suggestions among many memory tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the burden. It only states 'review mined patterns' without detailing what happens (e.g., returns a list, marks patterns as reviewed, allows interaction). This is minimal transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, front-loaded sentence with no extraneous information. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of an output schema (unprovided) and the workflow context with sibling tools like 'approve_candidate' and 'reject_candidate', the description is too minimal. It does not explain what 'review' entails operationally, leaving the agent without expectations for interaction.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, and the schema coverage is 100%. The description adds no parameter meaning, but with zero parameters, a baseline of 4 is appropriate as it doesn't need to compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'review' and the resource 'mined patterns that are ready for promotion', distinguishing it from sibling tools like 'approve_candidate' or 'reject_candidate' which involve actions after review.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives like 'audit_history' or 'mining_status'. The description implies it is for reviewing patterns ready for promotion but does not provide when-not-to-use or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden, but it only states the basic effect. It does not disclose side effects, reversibility, permissions, or what 'hot cache' entails.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that is front-loaded with the key action and resource. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has only one parameter, high schema coverage, and an output schema, the description covers the basic purpose. However, lack of behavioral details leaves some gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the description adds no extra meaning beyond the parameter's schema description. Baseline score applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('promote'), resource ('memory'), and destination ('hot cache for instant recall'). It distinguishes itself from siblings like warm_cache by specifying 'manually'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies manual promotion but does not explicitly state when to use this tool over alternatives like warm_cache or demote. No exclusions or context are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It discloses that merging keeps the most accessed/valuable representative, but does not mention destructive nature (loss of merged memories), permissions needed, or whether the operation is reversible. The dry_run parameter is mentioned in schema but not highlighted in description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences and contains no fluff. Every sentence adds value: first states purpose, second explains the merging logic and selection criteria.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has an output schema (not shown) and the description adequately covers the core functionality. However, being a mutation tool with no annotations, it lacks details on safety (e.g., reversibility, permissions, side effects). More context would be beneficial.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents both parameters. The description adds context about keeping the most accessed/valuable representative but does not further explain parameter usage beyond what the schema provides. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool consolidates similar memories by merging near-duplicates, specifying the verb (consolidate/merge) and resource (memories). It distinguishes from siblings like preview_consolidation (which only previews) and run_cleanup (different operation).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for merging duplicate memories but does not explicitly state when to use this tool versus alternatives like preview_consolidation or run_cleanup. There is no 'when not' guidance or mention of prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It only states 'Bulk reject... at once' but does not disclose whether rejection is destructive, reversible, requires permissions, or what side effects occur. Major gaps for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two efficient sentences: first states purpose, second provides parameter guidance. No fluff, front-loaded, every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Output schema exists but description does not explain return values. For a mutation tool, missing information on what happens to rejected candidates (deleted? marked?) and any prerequisites. Incomplete given tool complexity and lack of annotations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear parameter descriptions. Description adds value by suggesting mutual exclusivity ('either...or') and providing an example for pattern_type_prefix, improving agent understanding beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'reject', resource 'mining candidates', and scope 'bulk' and 'multiple at once'. Distinguishes from sibling 'reject_candidate' (singular) and 'approve_candidate' (different action).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description implies usage for rejecting multiple candidates but does not explicitly contrast with the singular 'reject_candidate' or state when not to use. It provides parameter choice guidance ('either pattern_ids or pattern_type_prefix') but lacks clear when-to-use vs alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description indicates a read-only operation, which is adequate for a simple info tool. However, it does not disclose any potential side effects or behavioral nuances beyond the basic function.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that front-loads the core purpose. Every word contributes meaning without any extraneous content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters and the presence of an output schema, the description sufficiently explains the tool's function. It is complete for a simple informational tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so according to guidelines the baseline score is 4. The description does not need to add parameter information, and none is missing.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves embedding provider and cache information, with a specific verb and resource. It distinguishes itself from sibling info tools like 'db_info' or 'memory_stats' by focusing on embeddings, though not explicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as 'hot_cache_status' or 'predictive_cache_status'. The description only states what it does without offering context on appropriate use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description details how content is split (paragraphs, list items), but lacks information on idempotency, error handling, or whether it overwrites existing memories. No annotations are provided to supplement.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, front-loaded with purpose, and uses a bullet list for splitting rules. It could be slightly more compact, but is clear and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema details are needed (but it exists), the description covers splitting rules well. However, it omits edge cases like empty content or memory limits, which are important for a bulk import tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds value for 'content' by explaining parsing, but does not expand on 'memory_type' or 'promote_to_hot' beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's verb ('seed') and resource ('memories from text content'), and explains it parses content into individual memories. It distinguishes from 'seed_from_file' by focusing on text input.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions 'useful for initial setup or bulk import,' providing some context. However, it does not explicitly state when not to use it or compare with alternatives like 'remember' or 'seed_from_file'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description provides some behavioral info (storing and optional promotion) but does not disclose side effects, required permissions, or what happens to the original candidate. It is moderately transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single 14-word sentence that captures the core functionality with no wasted words. It is front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity and the presence of an output schema, the description is adequate but assumes domain knowledge (e.g., what a mined pattern is). It could be more complete for users unfamiliar with the domain.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description adds no extra meaning beyond the schema. The description does not explain parameters or provide additional context, so it meets the baseline without improvement.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'approve' and the resource 'mined pattern', and specifies the actions: storing as memory and optionally promoting to hot cache. This distinguishes it from sibling tools like reject_candidate or promote.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not explicitly state when to use this tool versus alternatives. It lacks guidance on prerequisites or scenarios, though the tool name provides some implicit context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It only mentions the tool retrieves data but does not specify if it is read-only, requires special permissions, or has rate limits. The read-only nature is implied but not confirmed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the primary purpose, and includes relevant examples without extraneous text. Every sentence contributes meaning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has only two parameters (both well-documented in the schema) and an output schema exists, the description adequately covers the tool's function and utility. No additional behavioral or return information is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Both parameters have complete descriptions in the schema (100% coverage). The description adds no additional meaning beyond the schema; it mentions example operation types which are also listed in the schema, so no extra value is provided.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves recent audit log entries for destructive operations, specifying the verb 'get' and resource 'audit log entries'. It lists example operations, distinguishing it from siblings like get_session or get_sessions which serve different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description says 'Useful for understanding what changed and when', which implies usage context but does not explicitly state when to use this tool versus alternatives or when not to use it. No exclusions or comparisons are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses the Markov chain method and prerequisite but does not describe output format, side effects, or error states. Adequate but not detailed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three short sentences are concise and front-loaded. First sentence states purpose, second explains method, third gives prerequisite. Efficient yet slightly flat in structure.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With an output schema present, the description adequately covers purpose, method, and prerequisite. Missing output description is compensated by schema. Suitable for a prediction tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers 100% of parameters with descriptions, so baseline is 3. The description adds no extra meaning beyond schema; it only mentions an environment variable, which is not a parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool predicts next memories based on access patterns using a Markov chain. Verb 'predict' and resource 'memories' are specific, and the function is distinct from siblings like `predictive_cache_status`.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description mentions required environment variable `MEMORY_MCP_PREDICTIVE_CACHE_ENABLED=true` but provides no explicit when-to-use or when-not-to-use guidance, nor alternatives. Usage is implied but not fully clarified.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that the memory is not deleted but kept in cold storage, which is a key behavioral trait. However, no annotations are provided, and details on reversibility or side effects are missing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded, zero wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity and the presence of an output schema, the description is fairly complete, though it could mention that the operation is reversible or whether it triggers background processes.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, but the description adds no new meaning beyond the schema's parameter description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (remove) and resource (memory from hot cache), and distinguishes it from siblings like 'promote' and 'forget'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as 'forget' or 'invalidate_memory'. The description only states what it does.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the burden of behavioral disclosure. The description does not mention whether the operation is read-only, has side effects, rate limits, or any other behavioral traits beyond stating it 'shows' data.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences, front-loaded with the primary action, and every sentence adds value: what it does, what it shows, and why it's useful. No superfluous text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity (2 params, no nested objects, output schema exists), the description covers essential aspects: purpose, content of results, and utility. It lacks prerequisites or limitations but is sufficient for a read-oriented retrieval tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with both parameters having descriptions. The tool description does not add additional meaning beyond the schema, so baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves trust adjustment history for a memory and specifies it includes reasons, timestamps, and context. This verb-resource combination is distinct from sibling tools like get_contradictions or get_related_memories.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description says 'Useful for understanding why a memory's trust score evolved,' providing clear context for use. It does not explicitly state when not to use or mention alternatives, but the tool is straightforward and siblings are distinct.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. It mentions creating a CONTRADICTS relationship but does not disclose side effects (e.g., reversibility, whether it modifies memories, permission requirements). For a mutation tool, more detail is needed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two short sentences front-loaded with the main action. No unnecessary words, and all information is relevant. It is appropriately sized and structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (two required integer parameters) and the presence of an output schema (not shown but indicated), the description covers the basic purpose and usage context. It could be slightly more complete by mentioning the relationship direction or other nuances, but it is sufficient for typical use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (both parameters described in schema). The description does not add any semantic meaning beyond the schema's 'First memory ID' and 'Second memory ID'. No additional context about order or symmetry is provided, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Mark' and the resource 'two memories as contradicting each other', explicitly creating a CONTRADICTS relationship. This distinguishes it from sibling tools like 'link_memories' (which creates a LINK) and 'resolve_contradiction' (which resolves contradictions).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description specifies when to use the tool: 'when you discover that two memories contain conflicting information about the same topic.' It provides clear context but does not explicitly mention when not to use it or name alternatives. Given the sibling list, these are implied, so it is still helpful.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It describes the tool as returning observable metrics, implying a read-only operation. However, it does not explicitly state that no data is modified, nor does it mention rate limits or authentication requirements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured. The first sentence states the purpose, followed by a list of metric categories. The last sentence summarizes use cases. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters and an existing output schema, the description adequately covers the tool's purpose and metrics categories. It could mention that the output is a JSON object with the listed keys, but it is not critical.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0 parameters with 100% coverage. The description adds no parameter information because there are none. Per guidelines, baseline is 3 when schema coverage is high.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'observability metrics' for monitoring and debugging. It lists specific categories of metrics. However, it does not differentiate from sibling tools like memory_stats, mining_status, or hot_cache_status that may also provide similar metrics.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit use cases: debugging performance issues, monitoring usage patterns, and understanding system behavior. It does not mention when not to use this tool or alternatives, but the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It clearly explains the recall modes, thresholding, and result counts, and mentions that it returns confidence levels and hallucination-prevention guidance. However, it does not explicitly state that the tool is read-only or discuss potential side effects, though the nature of a search tool makes this largely clear.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured, with a clear summary of purpose followed by bullet-pointed mode details. Every sentence adds value, and there is no redundant or unnecessary text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the core functionality and modes but does not explain advanced features like include_related and expand_relations, which are important for a tool with 7 parameters. An output schema exists, so return values need not be detailed, but the description could be more complete regarding optimal parameter combinations or knowledge graph integration.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the description adds minimal value beyond the schema. The description repeats mode definitions already present in the schema and does not elaborate on parameters like include_related or expand_relations. The baseline score is appropriate given high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool performs 'semantic search with confidence gating and composite ranking,' and details three modes with specific thresholds and result counts. It distinguishes itself from sibling tools like recall_by_tag and recall_with_fallback by focusing on semantic similarity rather than tag-based or fallback approaches.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains the three modes and their use cases (precision, balanced, exploratory) but does not explicitly specify when to use this tool versus alternatives such as recall_by_tag or recall_with_fallback. The guidance is implicit through the mode descriptions, but lacks explicit directives on appropriate contexts or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Describes operation as a set/update, which is a write operation. However, without annotations, the description should disclose more about side effects (e.g., overwrites existing topic), authorization needs, or idempotency. The presence of an output schema partially compensates but isn't described.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the action. The second sentence provides context without being overly verbose. Could be slightly tighter but is effective.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple two-parameter setter with full schema coverage and an output schema, the description is adequate. It explains purpose and usage context. No major gaps identified.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents both parameters. The description adds no extra semantics beyond what the schema provides. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the specific verb 'Set or update' and the resource 'topic for a conversation session'. Distinguishes this tool from siblings like get_session (retrieve) and summarize_session (summarize) by focusing on topic assignment.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies usage when a topic needs to be set or updated on a session. States that topics can be auto-detected or manually set, providing context but no explicit exclusion or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds behavioral context beyond the schema by explaining the conditional behavior: if relation_type is specified, only that relationship is removed; otherwise, all relationships between the two memories are removed. This is valuable for agent decision-making.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two short sentences, front-loaded with the action. Every word adds value, and it is efficient in conveying the core logic.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the key behavioral nuance and parameter behavior. However, it lacks information about error conditions, prerequisites (e.g., existence of memories), or side effects of removal. For a mutation tool with no annotations, this leaves some gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already documents each parameter. The description rephrases the behavior for relation_type but does not add new semantic details about the parameters themselves (e.g., constraints or examples).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Remove relationship(s) between two memories', using a specific verb and resource. It also distinguishes the tool from its sibling 'link_memories' by being the reverse operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not explicitly state when to use this tool versus alternatives, nor does it provide prerequisites or exclusions. The nuance about specifying relation_type is present but offers no guidance on when to choose this tool over others.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses that results are sorted by session count and total accesses, but does not mention side effects, auth needs, or rate limits. It lacks explicit read-only confirmation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences with no wasted words. Front-loaded with the action and resource, followed by use case and output format. Efficient and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of an output schema, the description appropriately omits detailed return info. It covers parameter semantics and usage context. Minor gap: no distinction from 'access_patterns' sibling, but overall sufficient for a simple tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% (parameter min_sessions has description). The tool description adds context about pattern importance across sessions, but does not significantly enhance understanding beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb 'find' and resource 'content patterns appearing across multiple conversation sessions'. It distinguishes from the sibling 'access_patterns' by emphasizing cross-session scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description advises using the tool for identifying topics that 'might warrant promotion to hot cache', providing a clear use case. However, it does not explicitly state when not to use it or mention alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It implies a read operation ('Get') but does not explicitly state safety, side effects, or other behavioral traits. Adequate but not detailed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence of 9 words, front-loaded with verb and resource, no redundancy. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Low complexity tool with output schema present. Description covers the key information (schema version and size). Could mention additional context like health status but is sufficient given output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist (0 params), so the baseline is 4. The description adds value by specifying what information is returned ('schema version and size'), which enriches understanding beyond the empty input schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get', the resource 'database information', and specific details 'schema version and size'. It distinguishes itself from sibling tools like 'embedding_info' or 'memory_stats' by its generic info-gathering nature.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use or avoid this tool, or how it compares to alternatives. Usage is implied as a general database info check, but no when-not-to or context provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. Describes semantic similarity search but omits side effects, permissions, or read-only nature. Adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Four sentences, each informative: purpose, mechanism, usage. No fluff or repetition. Front-loaded with core function.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Has output schema, so return values are covered. Description addresses purpose, usage, and basic behavior. Could mention non-destructive nature, but overall complete for a search tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers all 3 parameters with descriptions (100% coverage). Description adds minimal value beyond schema, only reinforcing that high similarity indicates same topic area. Baseline score applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it finds memories that may contradict a given memory, with specific verb 'find' and resource 'memories that may contradict'. It distinguishes from sibling 'get_contradictions' by implying search versus retrieval.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit use cases: 'Use this after storing a new memory or when validating existing ones.' Does not mention when to avoid or alternatives, but context is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description lacks disclosure of side effects, permissions, or rate limits. Only states it returns flagged pairs, which is minimal for a read operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three short sentences front-loaded with key information. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Sufficient for a simple retrieval tool with no parameters and an output schema. Provides return type and next step.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters, so baseline 4. Description adds no parameter info, but none needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it retrieves all memory pairs marked as contradictions. Distinguishes from sibling like resolve_contradiction by referencing it for handling.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Indicates to use resolve_contradiction after retrieving, providing a clear workflow. No explicit when-not-to-use, but sufficient for a simple retrieval tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries full burden. It states the tool returns related memories and relationship info, implying a read operation, but does not disclose any side effects, authentication needs, or performance characteristics. Minimal disclosure beyond the basic action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, each adding distinct value: first states the core function, second adds detail and use case. No redundant or extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given full schema coverage and an output schema, the description is fairly complete. It covers purpose, return value, and a use case. However, it could include more context about graph traversal behavior or prerequisites, but not critically missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so each parameter is already documented. The description adds general context about relationship information but does not provide additional detail or examples for parameter usage beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the verb 'Get' and resource 'memories related to a given memory', and mentions returning relationship information. It distinguishes from sibling tools like list_memories or recall by focusing on graph exploration, as noted in 'explore the knowledge graph around a specific concept'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes a usage hint: 'Use this to explore the knowledge graph around a specific concept.' This provides context but does not explicitly exclude alternatives or state when not to use it, leaving room for improvement.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but the description uses non-destructive verbs ('Get', 'Shows') and indicates it's an analytical read-only operation, which is transparent enough for a stats tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three concise sentences front-loading the main action and adding value with no fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has an output schema and only two parameters, the description is sufficiently complete, covering purpose and value without needing to detail output format.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear parameter descriptions, so baseline 3. The description adds no additional parameter semantics beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states 'Get retrieval quality statistics' and explains that it shows which memories are frequently retrieved and used, distinguishing it from siblings like memory_stats or access_patterns.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for evaluating memory retrieval quality but does not explicitly state when to use vs. alternatives or when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses that the tool extracts patterns and updates a table with occurrence counts, and notes project-scoping. However, it does not mention side effects like potential performance impact or whether prior data is cleared, leaving some behavioral aspects implicit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with three sentences, each serving a distinct purpose: stating the main action, detailing outputs, and clarifying scope. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that an output schema exists (signal indicates yes), the description does not need to explain return values. It adequately covers the core functionality and scope, though it could mention prerequisites or frequency constraints for a more complete picture.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema covers the only parameter (hours) with full description. The description adds no extra semantics for the parameter beyond what is in the schema, so a baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it runs pattern mining on recent output logs, extracting specific pattern types (imports, facts, commands, code) and updating the mined_patterns table. It uses specific verbs and resources, and distinguishes itself from sibling tools like mining_status by detailing the extraction and update operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions that mining is project-scoped and processes recent logs, but it does not explicitly specify when to use this tool versus alternatives, nor does it provide conditions for use or exclusion criteria. Some context is implied but lacks direct guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that it reads files, extracts memories based on content structure (headers/lists for markdown), and supports markdown/plain text. However, it does not mention potential side effects (e.g., duplicate detection, overwrite behavior), file size/encoding limits, or authentication requirements, leaving gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise: three sentences that front-load the purpose, then explain the extraction logic and a common use case. Every sentence contributes meaningful information without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (3 parameters, output schema exists, 100% schema coverage), the description adequately covers the core functionality and use case. It explains file format support and extraction logic. However, it could mention prerequisites (file existence, readability) or potential errors, making it slightly incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the structured descriptions already document each parameter. The description adds context about the overall operation (reading file, extracting structure) but does not elaborate on parameter-specific constraints or usage beyond what the schema provides. Thus, it meets the baseline but adds no extra semantic value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Seed memories from a file', specifying the verb and resource. It distinguishes from the sibling tool seed_from_text by focusing on file input, and provides a concrete common use case (import from CLAUDE.md), making the purpose immediately understandable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains the tool reads files and extracts memories based on content structure, supporting markdown and plain text. It gives a common use case (import from documentation), which implies when to use it. However, it does not explicitly state when not to use it or compare with the alternative seed_from_text, missing a clear exclusion.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must cover behavioral traits. It describes the grouping logic and output categories (decisions, insights, action items, context), implying a read-only review operation. However, it does not mention error handling, permissions, or side effects, leaving some gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two paragraphs: first states purpose, second lists categories and usage guidance. It is front-loaded, each sentence adds value, and there is no redundant or verbose content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has a single parameter and an output schema (context signal), the description adequately explains what the tool does and when to use it. It covers the output categories and use cases. Missing details about error conditions (e.g., session not found) but overall complete for its simplicity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (one parameter 'session_id' with clear description). The tool description adds context about what the summary includes but does not add further semantics about the parameter itself. With high schema coverage, baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Summarize a session's key decisions, insights, and action items' and specifies grouping by semantic categories, distinguishing it from siblings like 'get_session' or 'remember'. It also mentions a use case relative to 'end_session()'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Use this before end_session() to review what was captured, or anytime to get a structured view', providing clear context for when to use the tool. Does not explicitly mention when not to use or list alternatives, but the guidance is helpful.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility. It states the tool returns validation status and details, but lacks specifics on side effects (likely read-only), rate limits, or database interaction. This is adequate for a simple check but could be richer.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with three sentences. The first sentence front-loads the purpose, and subsequent sentences add necessary context. Every sentence contributes value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter tool with an output schema, the description is sufficient to understand its function and context. It could mention that it's a safe read operation, but the simplicity of the tool reduces the need for more.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has no parameters, and schema description coverage is 100% (trivially). The description implicitly clarifies that no parameters are needed because the tool checks internal state, but adds no further parameter semantics beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool checks if the embedding model has changed since database creation, specifying the action and resource. It differentiates from siblings like embedding_info or db_info by focusing on change detection and compatibility implications.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use the tool (when model or dimension might have changed) and hints at consequences (need for re-embedding). However, it does not explicitly exclude scenarios or compare to siblings like db_maintenance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries full burden. It explains the consolidation process, salience scoring, and threshold promotion, providing good behavioral insight. Minor lack of detail on session termination side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with a lead sentence, analogy, details, and usage guidance. Each sentence adds value, though it could be slightly more concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the output schema exists, the description covers the primary purpose, process, and usage. It lacks potential edge cases (e.g., session resumability) but is reasonably complete for the tool's function.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds contextual understanding of the promotion process but does not significantly enhance parameter meaning beyond what schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it ends a session and consolidates episodic memories, with specific verb and resource. It distinguishes from siblings like 'get_session' and 'promote' by explaining the end-of-session consolidation process.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly advises 'Use this at the end of a conversation to preserve valuable learnings,' giving clear context. While it doesn't name alternatives, the guidance is sufficient for appropriate use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses that results are sorted by hot_score, lists all returned metrics with meanings (hits, misses, evictions, promotions, effectiveness, avg_hot_score). No contradictory or unexpected behavior implied. Lacks mention of potential latency or data freshness.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Very concise: one sentence for purpose, then a bullet list of returned fields. Every sentence adds value. Front-loaded with main purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 0 parameters and no annotations, the description fully covers what the tool does and returns. With an output schema (implied), the description explains the structure adequately. No gaps for this simple tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 0 parameters, so baseline is 4. Description adds value by detailing what the output contains, which is useful given no input parameters. It compensates for lack of schema complexity.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Show current hot cache contents, stats, and observability metrics.' It uses a specific verb ('show') and identifies the resource ('hot cache') with distinct content (stats, metrics). This distinguishes it from sibling tools like predictive_cache_status and memory_stats.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives. The description only explains what it does, not when to choose it over siblings like metrics_status or predictive_cache_status. No when-to-use or when-not-to-use information.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must carry the full burden. It indicates a read-only operation ('get status') but does not explicitly confirm non-destructive behavior, mention required permissions, or describe rate limits. The behavioral clarity is adequate but incomplete.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with no redundant information. The first sentence defines the purpose, the second adds specific details. Every word contributes.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple status tool with no parameters and an existing output schema, the description fully captures the purpose and returned information. No additional details needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the description adds value by explaining what the tool returns. Baseline for no parameters is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves status of the predictive hot cache system, listing specific details like enabled state, configuration, and learned pattern statistics. It distinctly differs from siblings like 'hot_cache_status' and 'metrics_status' by focusing on predictive caching.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for checking predictive caching state but lacks explicit guidance on when to use this versus alternatives (e.g., 'hot_cache_status' or 'metrics_status'). No contraindications or preferred contexts are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears the full burden. It discloses the behavioral consequence of making the memory eligible for auto-eviction, which is the key effect. It does not discuss reversibility or permissions, but for a simple operation this is adequate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single 11-word sentence that is front-loaded with the action and resource, with zero wasted words. It is appropriately sized for the simple operation.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one integer parameter, no nested objects, output schema present), the description covers the core purpose and effect. The sibling tools list provides context, and the description is sufficient for an agent to understand when and how to use it.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the schema already describes the 'memory_id' parameter as 'ID of memory to unpin'. The description adds no further meaning beyond what the schema provides, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Unpin' and the resource 'a memory', and explains the effect 'making it eligible for auto-eviction from hot cache'. This distinguishes it from the sibling 'pin' tool which would have the opposite effect.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage (when you want to allow a memory to be evicted) but does not provide explicit when-not-to-use guidance or mention alternatives like 'forget' or 'pin'. The purpose is clear enough for an agent to infer context, but lacks explicit direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It discloses the effect (prevents eviction) and precondition (must already be in hot cache), but does not mention reversibility, limits, or side effects. Adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise paragraphs with front-loaded purpose. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the operation's purpose, precondition, and effect. Given an output schema exists, return values need not be explained. It could mention reversibility but is largely complete for a simple action.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with one parameter 'memory_id' described as 'ID of hot memory to pin.' The description adds the constraint that the memory must already be in hot cache, providing meaning beyond the schema baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'pin' and the resource 'hot cache memory,' specifying the action of preventing auto-eviction. It distinguishes from the sibling tool 'unpin' by describing the opposite effect.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use pinning (to keep memories in hot cache during space pressure) and explicitly notes the precondition 'Only works on memories already in hot cache.' It does not mention alternatives or when not to use, but the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses that only memories not already in hot cache are promoted and requires a specific environment variable. This is good but could mention error behavior if the env is false or prediction fails.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with four sentences, each adding essential information. It starts with the main purpose, then clarifies scope, a constraint, and a prerequisite. No redundant text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity and presence of an output schema, the description covers key aspects: main action, constraint, and prerequisite. It could be slightly more complete with behavior on failure or env variable not set, but it is adequate for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The parameter schema includes a basic description ('Memory ID to predict from'), and the description adds context by explaining that this ID is used for prediction and subsequent promotion. With 100% schema coverage, a baseline of 3 is appropriate, but the description adds value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's verb ('Pre-warm'), resource ('hot cache'), and specific action ('promotes predicted memories'). It distinguishes from sibling tools like 'promote' and 'predict_next' by focusing on predicted memories that are not already in cache.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implicitly suggests usage when predictive caching is needed and notes a prerequisite (env variable). However, it does not explicitly state when to use this tool versus alternatives like 'promote' or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully bears the burden of behavioral disclosure. It clearly explains the tool's operation (pattern retrieval with optional memory filtering) and the prerequisite environment variable. No mentions of side effects, auth needs, or rate limits, but for a read-only cache status tool this is acceptable.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is brief (5 sentences) and front-loaded with the core purpose. Each sentence adds value: purpose, conditional behavior, and prerequisite. No redundancy or filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 3 fully documented parameters and an existing output schema (per context signals), the description covers all necessary context: what the tool does, when to use which parameter, and a critical prerequisite. Sufficient for correct agent invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for all parameters. The description adds minimal extra meaning beyond schema: it contextualizes memory_id (shows patterns from that memory vs all) and implies limit and min_count are for filtering. Baseline 3 is appropriate given the schema already documents parameters well.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool retrieves learned access patterns for predictive caching, with distinct behavior for specific memory_id versus all memories. This is a specific verb+resource combination that differentiates it from sibling tools like 'warm_cache' or 'predictive_cache_status'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit context on when to use with memory_id vs without, and highlights the required environment variable MEMORY_MCP_PREDICTIVE_CACHE_ENABLED=true. Does not explicitly mention when not to use or compare to siblings, but the guidance is sufficient for correct invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for behavioral disclosure. It transparently states the tool compacts database, updates query planner statistics, and demotes stale hot memories conditionally. This adequately informs agents of the mutation and side effects, though it could mention potential performance impact.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise, with two sentences that front-load the key operation and then elaborate. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no parameters and an output schema exists, the description is complete. It explains all three maintenance actions and their purposes (reclaim space, update stats, demote stale memories), meeting the needs for a parameterless tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no parameters (0 params), so schema coverage is 100%. The description adds value by listing the three operations (vacuum, analyze, auto-demote) that define what the tool does, but baseline score is 4 due to lack of parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool runs database maintenance (vacuum, analyze, auto-demote stale), using specific verbs and resources. It distinguishes itself from sibling tools like db_info or db_rebuild_vectors by specifying distinct maintenance actions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for database compaction, statistics update, and demotion of stale hot memories, but lacks explicit guidance on when to use vs. alternatives (e.g., db_info for querying, db_rebuild_vectors for vector rebuilding) or context like frequency or cautionary notes.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description adds behavioral context: it 'helps improve ranking by tracking which memories are valuable.' This explains the effect beyond the simple action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the core action, followed by usage guidance and benefit. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the output schema existing and the tool's simplicity, the description covers the essential context: when to use, what it does, and why it matters.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema coverage is 100% with clear descriptions for both parameters. The description adds no additional meaning beyond the schema, meeting the baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the action: marking a memory as used/helpful after recall. Distinguishes from siblings like 'recall' and 'remember' by specifying the post-recall feedback action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says when to call it: 'when a recalled memory was useful in your response.' No exclusions, but context is clear given the specific verb and resource.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It explains directionality and lists possible relation types with examples. Does not mention side effects or permissions, but operation is simple and non-destructive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is concise with a clear header, bulleted examples, and structured explanation. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations and presence of output schema, description adequately covers purpose, usage, and parameters. Could mention what the return value indicates, but not critical for tool invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but description adds value by providing examples and explaining the meaning of relation_type (enum-like values) and directionality (from_memory to to_memory).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Create a typed relationship between two memories' and provides examples showing directional relationships. It distinguishes itself from sibling tools like unlink_memories.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description states 'Use this to build a knowledge graph connecting related concepts' and explains direction and relation types. It does not explicitly state when not to use, but context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses non-destructive behavior ('without making changes') and that it shows clusters of similar memories. No behavioral contradictions; annotations not provided but description is adequate for preview functionality.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences front-loaded with purpose and usage. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for a simple tool: explains previewing clusters without changes. Output schema exists to detail return values, so description does not need to elaborate further.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers parameter 'memory_type' with description. Description adds no new parameter-specific detail beyond schema, but does mention output (clusters) which is beyond parameter scope. Baseline 3 for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the tool previews memory consolidation without making changes, showing clusters of similar memories that could be merged. Distinguishes from sibling tool 'run_consolidation' by indicating previewing nature.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly recommends using this before running actual consolidation to review changes, providing clear context for when to use the tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It details three operational steps: clearing vectors (memories preserved), re-embedding, and model info update. Also warns about time consumption. This is comprehensive behavioral disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured: one-sentence purpose, bullet-list of usage scenarios, numbered steps for behavioral transparency, and a concise warning. Every sentence adds value; no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has one parameter, an output schema (not shown), and no annotations. The description fully covers purpose, when to use, behavioral steps, and a caveat. No gaps identified given the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% for the single parameter 'batch_size' with a description. The tool description does not add further semantics beyond what the schema already provides. Baseline 3 is appropriate given high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states 'Rebuild all memory vectors with the current embedding model' – a specific verb and resource. The description lists specific use cases (switching models, fixing errors) that distinguish it from siblings like 'embedding_info' or 'db_maintenance'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly provides 'Use this when:' with three concrete scenarios (switching embedding model, fixing dimension mismatch, recovering from corruption). While it doesn't explicitly state when not to use or list alternatives, the guidance is clear and actionable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of behavioral disclosure. It explains the fallback order (patterns -> project facts -> all types) and stopping condition (min_results with medium+ confidence). It does not mention side effects, but as a recall tool, it is likely read-only.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three concise sentences with no fluff. The description is front-loaded with the core functionality and ends with usage guidance.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of similar tools (recall, recall_by_tag) and the existence of an output schema, the description provides sufficient information for correct usage. It explains the fallback mechanism and when to use this tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds value by specifying that the stopping condition is 'medium+ confidence', which is not in the schema. This adds meaning beyond the schema's parameter descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: recall with automatic fallback through memory types in a specific order. It distinguishes itself from siblings by advising use when unsure which memory type contains the answer.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit when-to-use guidance: 'Use this when you're unsure which memory type contains the answer.' It does not explicitly list when not to use or name alternative tools, but the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses read-like behavior (scans, parses) and details edge cases (empty repo, no markdown, file read errors, binary files). Could be more explicit about non-modification of files, but overall strong.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Concise and well-structured with a clear main sentence followed by bullet points of edge cases. Every sentence adds value, with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of an output schema and full parameter descriptions, the description is complete. It covers purpose, usage context, and edge cases, leaving no significant gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and description adds context: explains default file patterns, root_path, and the role of tags. This goes beyond the schema descriptions, enhancing understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: bootstrapping the hot cache from project documentation files. It specifies actions like scanning, parsing, and promoting, and the verb 'Bootstrap' is specific. It distinguishes from sibling tools like seed_from_file or warm_cache by focusing on batch processing of common documentation files.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly mentions ideal use case: 'when starting work on a new codebase.' However, it does not explicitly state when not to use it or compare with alternatives, which is a minor gap.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses trust score decrease, recording reason in history, default penalties per reason, floor at 0.0, and effect on recall rankings. No annotations present, so description fully covers behavioral details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Concise and front-loaded with main purpose. Bullet list adds structure but could be slightly more streamlined; still no unnecessary sentences.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers all aspects: purpose, when to use, behavior, parameters, trust mechanism. Output schema exists so return values are already defined. No missing details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions. Description adds value by detailing reason penalties and overriding behavior beyond schema, but schema already explains each parameter adequately.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Mark a memory as incorrect or outdated,' using a specific verb and resource. It distinguishes from sibling tools like 'forget' by focusing on invalidation rather than deletion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Use this when you discover that a recalled memory contains inaccurate or outdated information.' Does not mention when not to use, but the context is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses destructive actions (demotions, deletions, expirations) clearly. However, it does not explicitly mention that operations are irreversible or caution about potential data loss, leaving some behavioral ambiguity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured: a one-sentence summary, a bulleted list of actions, and a usage note referencing an alternative. Every sentence adds value with no redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given an output schema exists, the description does not need to explain return values. It covers the tool's scope, operations, and differentiation from siblings. However, it omits potential side effects like performance impact or locking during cleanup, which could be relevant for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, and the input schema is empty. Baseline is 4 per instructions. The description adds no parameter-specific meaning, but this is unnecessary given no parameters. The listed operations effectively explain what the tool does.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: comprehensive cleanup of stale data. It lists specific operations (demote, expire, delete) and distinguishes itself from the sibling tool db_maintenance, which is for database compaction only.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly recommends periodic use for keeping the database lean and advises using db_maintenance for compaction only. This provides clear when-to-use and when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses that trust score is capped at 1.0, records reason in trust history, and explains default boosts. This is transparent about the tool's effect, though it could mention if multiple validations stack or if there are any side effects beyond increasing trust score.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured: a clear first sentence states purpose, a second explains the effect, a third gives usage guidance, followed by a bullet list of reasons and a note about the cap. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (4 parameters, 1 required), the description is complete. It covers what the tool does, when to use it, parameter semantics with concrete examples, and behavioral details like the cap. An output schema exists but is not needed for completeness since the description covers return behavior implicitly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, but the description adds significant value by enumerating the three reasons with their default boosts and explaining how the 'boost' parameter overrides the default. This enriches the meaning of parameters beyond the schema entries.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action: 'Mark a memory as validated/confirmed useful.' It specifies the verb 'validate' and the resource 'memory', and distinguishes from sibling tools like 'invalidate_memory' and 'mark_memory_used' by focusing on increasing trust score and recording reason.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says 'Use this when you verify that a recalled memory is still accurate and helpful.' It also explains the different reasons and their default boosts, providing clear context for when to choose each. However, it does not explicitly mention when not to use the tool or compare it to alternatives like 'invalidate_memory'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavioral traits: the three resolution methods and their effects (creating relationships, weakening trust, deleting). This provides sufficient transparency for an agent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, with a clear first sentence stating the purpose, followed by a structured list of resolution behaviors. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of an output schema and the detailed explanation of resolution behaviors, the description provides complete context for this tool. All parameters are well-described in the schema, and the description adds the missing behavioral effects.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds value by explaining the resolution options in more detail and clarifying that keep_id must be one of the two memory IDs.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Resolve a contradiction') and the resource ('memory'), and distinguishes it from sibling tools like find_contradictions and mark_contradiction by focusing on resolution.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use after contradictions are identified, but does not explicitly provide when-not or alternative scenarios. However, the context of sibling tools makes the usage context clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

GitHub Badge

Glama performs regular codebase and documentation scans to:

Confirm that the MCP server is working as expected.
Confirm that there are no obvious security issues.
Evaluate tool definition quality.

Our badge communicates server capabilities, safety, and installation instructions.

Card Badge

Copy to your README.md:

[![memory-mcp MCP server](https://glama.ai/mcp/servers/michael-denyer/memory-mcp/badges/card.svg)](https://glama.ai/mcp/servers/michael-denyer/memory-mcp)

Score Badge

Copy to your README.md:

[![memory-mcp MCP server](https://glama.ai/mcp/servers/michael-denyer/memory-mcp/badges/score.svg)](https://glama.ai/mcp/servers/michael-denyer/memory-mcp)

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/michael-denyer/memory-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server