codex-agent-mem

by MarceloCaporale

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: v1.0.2
Disambiguation4/5
Most tools have clearly distinct purposes, but there is some potential overlap between retrieval tools like mem_get, mem_search, mem_recent, and mem_recent_changes. Descriptions help differentiate them, but the distinctions may still cause confusion.
Naming Consistency5/5
All tools follow a consistent mem_verb_noun or mem_noun_verb pattern in snake_case, making them predictable and easy to parse. No mixed conventions are present.
Tool Count3/5
28 tools is on the high side, covering a broad set of memory-related operations. While each tool has a defined purpose, the count feels slightly heavy for a single server.
Completeness3/5
The tool set covers many memory management aspects, but lacks explicit update and delete operations for stored observations (only create via mem_note_create). This creates a notable gap in the typical CRUD lifecycle.
Average 3/5 across 28 of 28 tools scored. Lowest: 1.9/5.
See the Tool Scores section below for per-tool breakdowns.
- No community issues in the last 6 months
- 0 commits in the last 12 weeks
- Last stable release on May 7, 2026
- No critical vulnerability alerts
- No high-severity vulnerability alerts
- No code scanning findings
- CI is passing
This repository is licensed under Apache 2.0.
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 provided. The description does not disclose any behavioral traits (e.g., read-only, destructive, auth requirements, side effects). Full burden falls on description, which is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence is concise and front-loaded, but lacks critical detail. Efficiency is undermined by vagueness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 6 parameters, no output schema, and no annotations, the description is far too brief. It omits return values, parameter semantics, and any behavioral context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 0% description coverage for 6 parameters. The description only vaguely references 'project' and 'hint', leaving current_cwd, repo_path, mentioned_files, and limit unexplained. Does not add meaning beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states it resolves a project and optional hint into candidates, but uses jargon ('persisted session/sub-scope candidates') that lacks clarity. It does not distinguish from sibling tools like mem_scope_guard or mem_search.
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. Only a vague mention of 'before requesting active context' but no explicit context or exclusions.
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 present, so the description must disclose behavioral traits. It only says 'Add one inheritance link', which is minimal. It does not mention idempotency, side effects, permissions, or limits.
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, which is concise, but it is too short to be informative. It sacrifices clarity and completeness for brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 5 parameters (3 required, with nested objects) and no output schema, the description is completely inadequate. It fails to explain essential details about the tool's behavior and usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description provides no information about the five parameters (project_key, source_project_key, mode, selector, enabled). This leaves the agent without guidance on how to use the parameters correctly.
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 'Add' and the resource 'inheritance link to a project', which is specific and distinguishes it from sibling tools like list and remove. However, it does not elaborate on what an inheritance link is, leaving some ambiguity.
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, when not to, or alternatives. The description simply states the action without 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 does not disclose whether this tool modifies state, requires specific permissions, or what side effects occur. The term 'apply' implies modification, but details are missing. With zero annotation coverage, the description should compensate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise. However, it could be restructured to front-load key information. It is not verbose but lacks clarity in the phrase 'derived repair event.'
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?
For a mutation tool with no output schema and no parameter descriptions, the description is too sparse. It does not explain the return value, error conditions, or what 'derived repair event' means. An agent would lack sufficient context to use the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 3 parameters with no descriptions. The tool description does not explain what project_key, repair_kind, or health_report_id mean. Schema description coverage is 0%, and the description adds no value for parameter understanding.
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 uses 'Apply' as a verb and 'repair proposal' as the resource, clearly indicating the action of applying a repair. However, the phrase 'as a derived repair event' is jargon and may confuse agents unfamiliar with the domain. It distinguishes from sibling mem_repair_propose by being the application step.
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 like mem_repair_propose or other repair tools. It does not specify prerequisites (e.g., must have a repair proposal first), context, 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.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries full burden. It mentions optimization for fewer tokens but does not disclose side effects, permissions, idempotency, or whether the pack is read-only. The behavioral traits are minimal.
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 that is front-loaded with the core purpose. It is concise without fluff, though could expand slightly on key behavior.
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 5 parameters, no output schema, and no annotations, the description is too brief. It fails to explain return format, error conditions, or parameter interactions, which are critical for correct usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% and the description adds no meaning to any of the 5 parameters (project_key, budget, max_chars, known_pack_hash, session_id). Agent cannot infer how to set them beyond their names and basic types/enums.
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 it returns a compact continuity pack to carry context forward with fewer tokens, which is a specific verb and resource. It distinguishes from siblings like mem_get by focusing on a 'pack' rather than a single context item, but could be more explicit about the exact format.
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 like mem_session_list or mem_get. The description lacks any context about prerequisites or suitability for different tasks.
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 the description must carry the full burden. It lacks disclosure of read-only nature, performance implications, or any side effects. The description implies a search operation but does not explicitly state behavioral traits.
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 single sentence is concise and to the point, but it could benefit from slightly more structure (e.g., listing parameters). Still, no waste.
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?
The description lacks return value information, pagination behavior, or result format, which is important for a search tool. Given the absence of output schema, more details are needed for completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description should compensate but only minimally hints at project_key and session_id. The 'query' and 'limit' parameters are entirely omitted, leaving the agent without crucial semantic info.
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 searches stored observations for a project or session, using specific verbs and resources. It distinguishes itself from sibling search tools like mem_get and mem_recent by focusing on searching within projects/sessions.
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. siblings (e.g., mem_get for direct retrieval). No mention of prerequisites or contexts where this tool is preferred.
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. The description lacks details on ordering, filtering, or whether it returns metadata or content. For a list tool, more behavioral info 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.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but lacks necessary detail. It is front-loaded but too brief to be fully effective.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and unexplained parameters, the description is incomplete. It fails to describe the return format or any operational details like pagination.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, and the description does not explain the parameters. It mentions 'for one project' but does not describe project_key or limit, leaving the agent without needed context.
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 'List' and resource 'memory snapshots', and specifies scope 'for one project'. It distinguishes from sibling tools like mem_snapshot_create and mem_snapshot_restore.
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 like mem_snapshot_create or mem_search. The description only states what it does, without context for when to use it.
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 provided, the description carries the full burden of behavioral disclosure, but it only says 'Add' without explaining side effects, permissions, idempotency, or what happens if a policy with the same kind already exists.
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 7-word sentence, which is extremely concise but at the cost of necessary information. It is under-specified for the complexity of the tool (4 params, nested object).
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 4 parameters, a nested object, no output schema, and no annotations, the description is severely incomplete. It does not explain the 'rule' object or any parameter behavior, making it insufficient for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description does not explain any of the 4 parameters (project_key, policy_kind, rule, enabled). It fails to add meaning 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 action 'Add' and the resource 'one memory policy' within a project. It is specific and distinguishes from sibling tools like mem_policy_list or mem_policy_remove.
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 guidance on when to use this tool versus alternatives, nor does it mention prerequisites or conditions for adding a policy. No context on 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.
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 states 'List' implying read-only, but fails to disclose pagination, ordering, or whether the list reflects current state exclusively. With zero annotation support, this is insufficient.
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 of 7 words—highly concise. However, conciseness is slightly undermined by missing critical details (e.g., return format) that could be added without significant verbosity.
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 27 sibling tools, the description does not sufficiently equip an agent to select this tool. It omits output schema details, does not explain what a 'memory policy' is, and lacks context on how the results integrate with other tools like mem_policy_add or mem_policy_validate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter `project_key` has 0% schema description coverage. The description adds the phrase 'for one project,' which contextualizes the parameter as a project identifier, but does not specify its format, constraints, or examples. This adds little beyond the schema's type declaration.
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 lists memory policies, specifying both active and inactive categories and targeting a single project. This provides a clear verb-resource pair and distinguishes it from other list tools like mem_inheritance_list, though it could further clarify what constitutes a 'policy'.
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?
There is no guidance on when to use this tool versus alternatives such as mem_policy_add or mem_policy_remove. No when-not-to-use or prerequisite information is provided, leaving the agent to infer context from the tool name alone.
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 provided, the description carries the full burden. It implies a read operation ('return') but does not disclose side effects, authentication needs, error behavior, or what happens if the project does not exist. 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 of 13 words, front-loaded action. No redundancy. However, slight under-specification given the lack of parameter details.
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?
Simple tool with 2 params, no output schema, no annotations. Description fails to define 'compact scope guardrails' or what the return value looks like. Lacks prerequisites or usage context, leaving the agent with significant ambiguity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It mentions 'optionally scoped to one persisted session' for session_id but does not explain project_key at all. No format, rules, or constraints beyond what the schema provides (type, required).
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 ('return'), the resource ('compact scope guardrails'), and the scope ('for one project, optionally scoped to one persisted session'). It distinguishes from siblings like mem_scope_resolve by using 'guardrails' implying a different output, but does not explicitly differentiate.
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 (e.g., mem_scope_resolve). No mention of prerequisites, context, or scenarios where this is preferred. The description only states what it does, not when to use it.
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 does not disclose any behavioral traits beyond the basic creation action. With no annotations provided, it fails to inform about permissions, side effects, or what 'versioned' implies operationally.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence is concise, but it omits critical information. Acceptable for a minimally viable description, but not optimally balanced.
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 three parameters, no output schema, and no annotations, the description is too brief. It lacks details on return values, error conditions, and operational semantics, leaving significant gaps for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description adds no meaning for any of the three parameters. It does not clarify the role of project_key, label, or session_id beyond their schema declarations.
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 ('Create'), the resource ('versioned memory snapshot'), and the scope ('for one project'). It effectively distinguishes from sibling tools like mem_snapshot_list and mem_snapshot_restore.
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 (e.g., mem_snapshot_list or mem_snapshot_restore). Missing context on prerequisites or postconditions.
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 disclose behavioral traits. 'Remove' implies destruction, but there is no detail on side effects, reversibility, permissions, or impact on related data. This is insufficient for a mutating operation.
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 with no unnecessary words. However, it could be structured to include more detail while remaining concise.
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 no annotations, no output schema, and minimal parameter explanation, the description is incomplete. The agent cannot fully understand the tool's behavior, return value, or when to use it, especially with many sibling tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must explain parameters. It does not mention project_key or policy_id at all, leaving the agent without context for what these parameters mean.
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 the resource ('one memory policy from a project'). It distinguishes from sibling tools like mem_policy_add and mem_policy_list, which have different verbs.
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 (e.g., mem_policy_add, mem_policy_list). No mention of prerequisites 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.
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. It only states 'Validate' without disclosing side effects, error handling, idempotency, or whether changes are made. For a validation tool, this is insufficient.
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 that is concise and to the point. However, it could be more structured (e.g., using bullet points or sections) without adding verbosity.
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 no output schema, no annotations, and low schema coverage, the description fails to provide enough context. Agents need to know validation criteria, expected errors, and prerequisites, which are missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description does not explain any parameters (policy_kind, rule). Agents have no guidance on valid values or the structure of the rule object, making invocation error-prone.
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 validates a memory policy definition before adding it, using a specific verb and resource. It distinguishes from siblings like mem_policy_add (adds) and mem_policy_list (lists). However, it lacks detail on what 'validate' entails (e.g., syntax, semantics).
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 phrase 'before adding it' implies sequential use with mem_policy_add, providing some context. But no explicit when-to-use or when-not-to-use, nor alternatives mentioned.
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 mentions 'defensive' behavior and avoiding project-wide packs for ambiguous containers, which gives some insight. However, it does not disclose side effects, authorization requirements, or what happens with invalid inputs. Since no annotations are provided, more detail would be beneficial.
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 of 18 words, concise and front-loaded with the main action. However, it uses jargon that might require background knowledge. Overall, it earns its space.
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 complexity (10 parameters, no output schema, no annotations), the description is too brief. It does not explain the return format, how hints work, or the role of budget/session_id, leaving significant gaps for correct tool use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Most of the 10 parameters are not explained in the description. Only 'thread/path hints' are vaguely referenced, but without mapping to specific parameters. With 0% schema description coverage, the description fails to provide meaningful parameter semantics.
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 'defensive startup context' and resolves scope from hints, which distinguishes it from siblings like mem_scope_resolve or mem_context_pack. However, the term 'defensive startup context' is somewhat vague and may not be immediately intuitive to all agents.
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 implies usage for startup when scope is ambiguous, but it provides no explicit guidance on when to use this tool versus alternatives like mem_scope_resolve or mem_context_pack. No when-to-use or when-not-to-use information is given.
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 fully disclose behavior. It mentions 'deterministic' implying no side effects, but does not specify whether it is read-only, requires permissions, or any other traits. The behavioral disclosure is minimal.
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 key action. No unnecessary words, and it effectively communicates the core 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?
For a tool with no output schema, no annotations, and 0% parameter coverage, the description is insufficient. It omits what a 'closure check' means, the format of the return value, and any prerequisites or usage constraints.
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 0%, and the description adds minimal meaning: 'one project' for project_key and 'optionally scoped to one persisted session' for session_id. This adds some context but does not fully compensate for the lack of schema descriptions.
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 a 'deterministic closure check for one project' with optional session scoping. It uses a specific verb and resource, distinguishing it from sibling tools like 'mem_note_create' or 'mem_search', though the term 'closure check' may require domain knowledge.
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, when not to use it, or prerequisites. The description only states the action without context for appropriate usage.
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 the transparency burden. It only states 'return a compact brief' without disclosing side effects, authentication needs, or what 'compact' means. The read-only nature is implied but not explicit.
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 zero filler. Every word earns its place, clearly stating action and optional parameter.
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?
The description is too sparse for a retrieval tool with no output schema. 'Compact brief' is vague; the return format and what constitutes a project are not explained. More context is needed given the many sibling 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 0%, but the description adds meaning by explaining session_id's role ('optionally scoped to one persisted session'). However, project_key remains completely undescribed, relying on the schema's type string only.
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 a compact brief for one project, with optional session scoping. However, it does not differentiate from sibling tools like mem_get or mem_context_pack.
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 over alternatives. The description implies retrieval of project briefs but provides no exclusions or context for decision-making.
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 present, and the description does not disclose behavioral traits such as read-only nature, authentication needs, rate limits, or side effects. It only states what is returned, not the tool's operational characteristics.
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, efficient sentence that immediately communicates the action and resource. While concise, it sacrifices explanatory depth, but for a tool with one parameter, it is appropriately sized.
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?
With no output schema, no annotations, and a single parameter, the description should explain the return value and any constraints. Terms like 'audit provenance' and 'original turn context' are undefined, leaving an agent uncertain about the tool's output and behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, yet the description does little to explain the observation_id parameter beyond implying it identifies an observation. It fails to clarify the format, source, or how to obtain valid IDs, which could lead to invocation errors.
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 ('Return audit provenance') and the specific resource ('for one stored observation'), including additional detail ('original turn context'). It distinguishes from sibling tools like mem_get (which likely returns the observation itself) and mem_search (which finds observations).
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. There is no mention of prerequisites, typical use cases, or conditions that would make provenance retrieval appropriate compared to other mem_ 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 exist, so the description must fully disclose behaviors. It only says 'list recent' with no mention of ordering, default limit, pagination, non-destructiveness, or error states. This is insufficient for an agent to anticipate tool behavior.
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, front-loading the action and resource. It is concise, though it omits essential details about parameters and behavior.
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 4 parameters, no output schema, and no annotations, the description is incomplete. It does not explain return format, parameter meanings, or behavioral traits like 'recent' definition, making it insufficient for reliable tool usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, yet the description provides zero explanation of the four parameters (project_key, limit, query, sub_scope_hint). An agent has no guidance on how to use them correctly.
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 uses a specific verb ('List') and resource ('persisted sessions/chats for one project'), and provides a clear purpose: 'so agents can select a scoped continuity lane.' This distinguishes it from siblings like mem_search or mem_get by narrowing to session/chat listing.
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 when an agent needs to pick a session for continuity, but does not specify when not to use, prerequisites, or contrast with alternatives such as mem_search or mem_context_pack.
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 convey behavioral traits. It only states the action without disclosing side effects, read-only nature, or error conditions, offering 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?
The description is a single, concise sentence with no unnecessary words. It is front-loaded with the essential action and resource.
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?
Without an output schema or additional context, the description fails to specify return format, pagination, or what constitutes inheritance links, leaving the agent underinformed for reliable invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description adds no meaning beyond the schema. It implies project_key identifies a project but omits format, 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?
Clearly states the action 'List' and resource 'inheritance links', scoped to 'one project', which effectively distinguishes it from sibling tools like mem_inheritance_add and mem_inheritance_remove.
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 mem_inheritance_add or other listing tools. The description lacks context about prerequisites or suitable 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?
With no annotations, the description must disclose behavioral traits, but it only states the basic operation. Missing details like idempotency, error handling, or side effects (e.g., if inheritance_id doesn't exist).
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 with no wasted words. However, it may be too terse, sacrificing necessary detail. Could be expanded slightly while maintaining 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 involves mutation and no output schema, the description lacks completeness: no mention of return values, confirmation, or error conditions. Does not adequately prepare the agent for safe 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 0%, so the description should compensate. It implies project_key identifies a project, but does not explain inheritance_id or its valid range (schema shows minimum 1). Some meaning added, but insufficient.
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 the resource ('one inheritance link from a project'). It effectively distinguishes from sibling tools like mem_inheritance_add (add) and mem_inheritance_list (list).
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, prerequisites, or alternatives. The agent has no context to decide appropriateness relative to other 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, and the description does not disclose whether the tool is read-only, requires permissions, or any side effects. It only states 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 a single, straightforward sentence that effectively communicates the core action. It is concise and front-loaded, though could benefit from more structure.
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 absence of an output schema, the description fails to explain what is returned. It also does not differentiate from sibling tools sufficiently, making it incomplete for an agent assessing completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The parameter 'observation_id' is described only as 'by id', adding no meaning beyond the schema. With 0% schema description coverage, the description should provide more context.
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' and the resource 'one stored observation', differentiating it from other tools that retrieve multiple observations or perform other 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 use for retrieving a single observation by ID but lacks explicit guidance on when to use it versus alternatives like mem_search or mem_recent.
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 must disclose behavioral traits. It fails to mention side effects (e.g., overwriting existing content), required permissions, or error conditions.
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, no verbosity. However, the lack of critical information makes it feel under-specified, not just concise.
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?
For a restore operation with 2 parameters and no output schema, the description fails to explain return values, error handling, or the relationship between project_key and snapshot_id. Incomplete for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 0% description coverage and the description does not explain the two parameters (project_key, snapshot_id). The agent receives no meaning beyond parameter names.
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 action (restore), resource (snapshot), and target (AGENTS.md continuity block). Distinguishes from siblings like mem_snapshot_create and mem_snapshot_list.
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 a precondition ('when the project root path is known') but lacks explicit when-not or alternative tools. However, the context is helpful and the sibling set suggests no direct alternative for restore.
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 responsibility for disclosing behavioral traits. It doesn't state that the operation is read-only, safe, or idempotent, nor does it mention any ordering or pagination 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?
The description is a single concise sentence with no wasted words, front-loading the main action. However, it could be slightly more informative without sacrificing brevity.
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 no output schema and no annotations, the description is incomplete. It does not clarify what 'observations' are, the meaning of 'recent' (time window), or the return format. For a tool with 3 optional parameters, more context 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?
With 0% schema description coverage, the description adds meaning by mentioning 'scoped to one project or persisted session', but does not explicitly describe the `limit` parameter or the semantics of `session_id` and `project_key`. The parameter names are somewhat self-explanatory.
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 'Return recent observations' with optional scoping by project or session. This verb+resource+scope pattern distinguishes it from siblings like mem_get (specific observation) and mem_search (query-based).
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 retrieving recent observations with optional filters, but lacks explicit guidance on when not to use it or alternatives. For example, it doesn't mention that mem_get is better for a single known observation.
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 states the tool is 'deterministic', implying no side effects, but lacks details on error handling, authentication needs, or behavior with invalid project keys. Given no annotations, more disclosure would be beneficial.
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, front-loaded sentence that efficiently conveys the tool's purpose and output without redundant 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?
The description lists report contents (duplicates, contradictions, etc.) but omits output structure, format, and additional context about project keys. For a tool with no output schema and 0% param coverage, more detail is needed for full completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description does not explain the 'project_key' parameter beyond its role. No format, constraints, or usage context is provided, leaving the agent to infer meaning.
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 'Return' and the resource 'health report', listing specific contents (duplicates, contradictions, etc.). It distinguishes from sibling tools like mem_health_runtime by specifying 'deterministic' and 'for one project'.
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 when-to-use or when-not-to-use guidance is provided. The description implies analysis use but does not differentiate from similar tools like mem_health_runtime 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?
With no annotations, the description provides some behavioral context (indexed, eligible for context packs), but lacks details on side effects, idempotency, permissions, or limits. It is 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?
A single sentence conveying the core purpose and key behaviors without any filler. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has six parameters (two required), no output schema, and no annotations. The description only covers high-level purpose, leaving parameter meanings and return behavior completely unspecified.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description provides no explanation of any of the six parameters (project_key, text, session_id, title, tags, importance). With 0% schema coverage, the agent relies solely on the description, which is insufficient.
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 one manual operational memory note', specifying the verb and resource. It also adds key behaviors: 'indexed for mem_search' and 'eligible for context packs', which distinguishes it from sibling tools like mem_get (retrieve) or mem_bootstrap_context (setup).
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 that this tool is appropriate when the goal is to create a note that will be searchable and included in context packs. However, it does not explicitly say when not to use it or compare with similar siblings like mem_open_work, so some guidance is missing.
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 provides substantial behavioral context: it returns a changelog of specific categories. It implies a read-only operation without side effects. However, it does not disclose how the 'last stable context sync' is determined or whether results are scoped to the project/session.
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, well-structured sentence that front-loads the key action and enumerates return categories. No unnecessary words or repetitions.
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 lack of output schema and 28 sibling tools, the description could clarify how this tool fits into the workflow (e.g., when to use after a sync) and explain return format. It lists categories but not structure. Adequate but not fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description provides no information about the two parameters (project_key, session_id) beyond what the schema offers. With 0% schema description coverage, the description fails to add meaning—e.g., what session_id does or why project_key is required.
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: returning changes since the last stable context sync, listing specific categories (new pending items, resolved work, blocker changes, DoD gap changes, new decisions). This is a specific verb-resource combination that distinguishes it from siblings like mem_get or mem_recent, which do not mention sync-related changelogs.
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 after a stable context sync, but does not explicitly state when to use this tool versus alternatives like mem_recent (recent changes) or mem_get (generic retrieval). No exclusions or prerequisites are given, leaving ambiguity for the agent.
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 indicates a read operation ('Return') but does not explicitly state whether the tool is read-only, idempotent, or has side effects. This is a gap, but the purpose implies non-destructive 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 that front-loads the action and resource. No wasted words; it efficiently conveys the tool's purpose.
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 single parameter and no output schema, the description is minimally complete. It explains the tool's action but does not describe the return format, any prerequisites (e.g., existing health report), or behavioral constraints. It is adequate but could be more informative.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 0% description coverage for the single parameter 'project_key'. The tool description does not explain what 'project_key' is or its format. This leaves the parameter underdocumented.
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 that the tool returns governed repair proposals based on the latest health report for a project. It uses a specific verb ('Return') and resource ('repair proposals'), and distinguishes from sibling tools like mem_repair_apply (applies repairs) and mem_health (returns health report).
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 in a workflow: first check health report (mem_health), then propose repairs (this tool), then apply (mem_repair_apply). However, it does not explicitly state when to use or when not to use this tool, nor does it mention alternatives or prerequisites.
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 must convey behavior. It mentions the tool returns 'deterministic' open work and can be scoped to a session, which adds some behavioral context. However, it does not discuss read-only nature, error handling, or what the output contains.
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, clear sentence of 12 words, front-loading the core purpose and optional scoping. 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 no output schema and many sibling tools, the description provides a high-level purpose but omits return format, potential errors, and how the tool fits into the larger workflow. It is adequate but not thorough.
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 0%, so the description must compensate. It clarifies that project_key identifies the project and session_id optionally scopes to a persisted session. This adds meaning beyond the parameter names and types, but lacks details on formats or valid values.
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 explicitly states the tool returns deterministic open work for a specific project, optionally filtered by a session. This clearly distinguishes it from sibling tools like mem_get (general retrieval) and mem_search (search).
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 this tool vs. alternatives. The purpose implies it's for retrieving open work items, but there is no mention of prerequisites, when not to use, or comparison with mem_get or mem_search.
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?
Since no annotations are provided, the description carries the full burden. It adequately indicates that the tool is a read-only health check (returns data without side effects), but it does not explicitly state that it is non-destructive or require any authentication. The behavioral traits are implied but not fully disclosed.
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, well-structured sentence of 15 words that efficiently conveys purpose and outputs. Every word earns its place, with no 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 zero parameters, no output schema, and no annotations, the description is reasonably complete. It lists key return fields, though it could mention that the output format is likely JSON or provide an example. Still, it is sufficient for an agent to understand the tool's function.
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, so the baseline is 4. The description adds value by listing the specific outputs (pid, uptime, etc.), which enriches understanding beyond the empty 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 that the tool returns runtime health information including pid, uptime, idle timeout, request counts, and exit diagnostics. It uses a specific verb ('Return') and resource ('runtime health'), and it distinguishes from the sibling 'mem_health' tool by specifying the focus on stdio MCP process runtime details.
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 'mem_health'. The description does not mention any prerequisites or context for invocation, leaving the agent without decision support.
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:

[![codex-agent-mem MCP server](https://glama.ai/mcp/servers/MarceloCaporale/codex-agent-mem/badges/card.svg)](https://glama.ai/mcp/servers/MarceloCaporale/codex-agent-mem)

Score Badge

Copy to your README.md:

[![codex-agent-mem MCP server](https://glama.ai/mcp/servers/MarceloCaporale/codex-agent-mem/badges/score.svg)](https://glama.ai/mcp/servers/MarceloCaporale/codex-agent-mem)

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/MarceloCaporale/codex-agent-mem'

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