Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate non-read-only and non-destructive. The description adds that it stores new information, but does not detail side effects, limits, or whether it appends or overwrites. Moderate value added.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, front-loaded with purpose, and includes a structured action guide. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple create tool with 3 parameters and an existing output schema, the description covers when to use and gives an example. Could mention return value or limits, but overall adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, but the description includes an example with content, category, and tags, giving semantic hints. However, it does not explain parameter types, requiredness, or constraints fully.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Store NEW information' and provides examples (preferences, decisions, facts), distinguishing it from siblings like update_memory, delete_memory, and search_memory.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The ACTION GUIDE explicitly says 'Use when saving new information for the first time' and gives an example. It could mention when not to use (e.g., for updates use update_memory), but it's still clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description states 'List archived memories', implying a read-only operation, but annotations set `readOnlyHint` to `false`, suggesting potential side effects. This contradiction is severe. The description provides no additional behavioral details (e.g., auth requirements, state changes) beyond the basic listing, so transparency is critically lacking.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: two clear sentences with an explicit action guide. It is front-loaded and contains no unnecessary words or repetitions.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description explains what 'archived' means and the intended use case, and an output schema exists. However, it lacks behavioral context (e.g., whether listing alters state) and does not mention related tools like `restore_memory`. This makes it adequate but not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has a single optional parameter `limit` with no description (0% schema coverage). The tool description does not mention this parameter or its purpose, failing to add meaning beyond the raw schema. Given the simplicity of the parameter, a score of 2 reflects the minimal gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'List' and the resource 'archived memories'. It further differentiates from siblings like 'list_memories' by explaining that this tool shows soft-deleted or automatically archived memories, making the purpose specific and distinct.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description includes an explicit 'ACTION GUIDE — when to use' section that specifies the context (soft-deleted or low-importance/recency memories). While it does not explicitly list when not to use or mention alternatives, the guidance is clear and sufficient for the intended scenario.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already signal mutability and idempotency; the description adds substantial behavior: sync requires sync_enabled and google_drive_client_id, warmup downloads ~570 MB, backfill is bounded to 100, and setup_sync uses Device Code OAuth. No contradiction with annotations, and side effects are disclosed in useful detail.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact, front-loaded with a summary, and uses a scannable bullet list. Every line adds a decision-relevant fact; no filler or repetition of schema fields.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-action polymorphic tool with zero schema descriptions, the description covers all actions, their prerequisites, parameters, valid keys, an example, and a safety-relevant bound. Outputs are not described, but an output schema exists, so the description is complete enough for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry parameter meaning. It enumerates all action values, documents key/value valid values with an example, and explains batch_size's bound. Minor ambiguity remains around how integer values are encoded in the string-typed value parameter, so it is not a perfect 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with the domain ('Server config, sync, setup, and bounded vector backfill') and then enumerates every action. This clearly identifies the tool's operations and separates it from the memory-focused sibling tools; the only near-relative config__open_relay is excluded by the explicit action list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The ACTION GUIDE gives clear per-action context, including prerequisites for sync, valid keys for set, and scope for backfill. It does not explicitly name alternative tools or say 'use config__open_relay instead', so it lacks formal exclusion guidance, but the context is strong enough for an agent to choose correctly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the burden of behavioral disclosure. It transparently reveals the browser-opening side effect, qualifies it with 'when possible', and lists the return contents. It does not detail failure modes or status semantics, but the core behavior is clearly disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single focused sentence that front-loads the main purpose and then covers side effects and return values. Every clause earns its place with no repetition or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

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 lack of meaningful user parameters, the description covers the action, side effect, and returned information sufficiently. A small gap is that it does not elaborate on what 'current status' means or what happens when the browser cannot be launched, but these are minor given the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The only parameter is 'ctx', an injected Context object rather than a domain-specific parameter. The schema itself provides extensive documentation for Context, and the description does not need to explain it. Adding parameter detail would add little value, so the baseline for effectively no user-facing parameters is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action ('Get'), a specific resource ('the relay configuration URL for mnemo-mcp'), and an additional behavior ('opening it in the user's browser when possible'). This clearly differentiates it from the sibling tools such as the generic 'config' and all memory-related tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context: this tool is for retrieving the relay configuration URL and attempting to open it in the browser. It does not name alternatives or exclusions, but the intended use case is readily inferable and no misleading guidance is present.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=false and destructiveHint=false, indicating modification but not destruction. The description mentions the requirement for LLM API keys, which is helpful, but does not detail what happens to original memories (e.g., deletion or merging). There is no contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very concise: two sentences plus a short usage guide. It is front-loaded with the core purpose and contains no unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema exists, return values need not be explained. However, the description lacks details about process side effects (e.g., whether original memories are removed or just summarized) and error conditions, which are relevant for a modification tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The only parameter 'category' has no description in the schema (0% coverage). The description provides an example usage but does not explain what values are valid or how the parameter is used beyond that.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses specific verb 'Summarize' and resource 'memories in a category', clearly distinguishing from siblings like add_memory or delete_memory. The example further clarifies the purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use: when a category has too many redundant memories and needs cleanup. It gives a concrete example. However, it does not mention when not to use or compare with other tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already signal destructiveHint=true, so the description's 'Remove' is consistent. It adds no further behavioral details (e.g., irreversibility or side effects). Since annotations cover the destructive nature, a score of 3 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: two short sentences plus an example. Every sentence serves a purpose with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity (single required parameter, destructive, with output schema available), the description covers purpose, usage context, and a concrete example. No essential information is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The only parameter, memory_id, has no schema description (0% coverage). The description provides a usage example (memory_id='abc123') but no semantic explanation beyond the parameter name. The name itself is clear, so marginal added value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'Remove a memory by ID', clearly indicating the action (remove) and resource (memory). This directly distinguishes it from sibling tools like add_memory, update_memory, and list_memories.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The ACTION GUIDE explicitly advises use when a memory is outdated, incorrect, or to be forgotten. It includes an example. While it does not mention alternatives or when not to use it, it provides sufficient context for proper selection among sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate readOnlyHint=false and destructiveHint=false, meaning the tool is not read-only nor destructive. The description adds that it exports all memories as JSONL, which implies a safe, non-destructive read-like operation. However, it does not disclose potential performance impacts or database locking behavior, which would be useful for low-latency scenarios.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very concise: two sentences, no extraneous information. The first sentence states the core functionality, and the second provides usage guidance. Information is front-loaded and each sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 0 parameters, an output schema, and annotations, the description is complete. It explains the output format (JSONL), the scope (all memories), and the use case (backup or raw dump). No additional information is necessary for an agent to correctly invoke this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0 parameters with 100% schema coverage, so the description does not need to explain parameters. Baseline for 0 parameters is 4, and the description adds no extra parameter info, which is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool exports all memories as JSONL, specifying the verb, resource, and output format. It distinguishes from siblings like import_memories and list_memories by explicitly calling it an export for backup or raw dump.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description includes an 'ACTION GUIDE' that explicitly states when to use: when the user requests a backup or raw dump. It does not explicitly state when not to use, but the context is clear, and the sibling tools cover other operations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the description's claim of providing 'documentation' is consistent but adds no new behavioral insight beyond the structured data. The description does not disclose additional traits like response size or caching behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: one sentence plus a one-line action guide. It is front-loaded with the key purpose and provides a clear call-to-action, with no redundant or irrelevant content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

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 annotations and an output schema (not shown), the description covers the basic usage context. However, it could be more complete by listing all supported topics or providing examples of what the documentation contains.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, yet the description only vaguely mentions 'topic: 'memory' | 'config'' without explaining the parameter's meaning, allowed values, or default behavior. This adds minimal value over the schema, leaving the agent unsure about possible or valid topics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool provides 'Full documentation for memory and config tools' and gives detailed instructions, which unambiguously defines its purpose as a help/reference tool. This distinguishes it from sibling tools like add_memory or config, which are the actual tools being documented.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The action guide explicitly says 'Use when you need detailed instructions on how to use specific server tools or features,' providing clear context for when to invoke this tool. However, it does not explicitly state when not to use it or list alternatives, though the sibling tools themselves imply the alternative of directly using them.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate it's not read-only and not destructive, but the description lacks details on behavioral traits such as whether the import overwrites existing data, what the 'merge' mode entails, or any error handling. It adds minimal value beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: two sentences plus an action guide with an example. It is front-loaded with the main action and structured efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 2 parameters and 0% schema coverage, the description provides a usage example but misses behavioral details like what the tool returns (despite an output schema existing) and how modes other than 'merge' behave. 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.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description provides an example showing 'data' as a JSON string and 'mode' as 'merge', adding some meaning. However, it doesn't explain other possible values for 'mode' or the format of the data array, so the compensation is partial.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Import memories from JSONL data or a list of objects', specifying the verb 'import' and the resource 'memories', which distinguishes it from siblings like 'add_memory' or 'export_memories'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description includes an explicit 'ACTION GUIDE — when to use' section: 'Use when restoring from a backup or migrating data into the memory system', providing clear context for usage. It does not mention when not to use, but the guidance is strong.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds filter behavior but does not disclose pagination, ordering, or other operational details.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, with the purpose in the first sentence and an example. Every sentence adds value, no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and good annotations, the description covers key aspects. Missing ordering or default behavior, but adequate for a simple list tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

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 explains 'category' and 'limit' through example but does not detail valid values or constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool browses memories with optional category filtering. It implies a broad listing, distinguishing it from siblings like search_memory, but does not explicitly name alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The ACTION GUIDE explicitly advises when to use: for broad views or category-specific listings, with an example. It lacks exclusionary guidance (when not to use) but provides clear context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already set destructiveHint=true, but the description adds rich behavioral context: requirements per action (e.g., 'Requires content' for add), side effects (archived, restore), and the fact that it is a persistent store. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is structured with sections (deprecation notice, action guide, workflow) and front-loaded with the deprecation warning. However, it is verbose and contains some repetition (e.g., 'Use specialized tools ... instead' appears twice). Could be more concise while retaining all information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (22 params, many actions, deprecation) and the presence of an output schema (so return values need not be described), the description covers the primary use cases well. It also explains the deprecation context and recommends granular alternatives. Missing details on less common parameters slightly reduce completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

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. The action guide explains key parameters for main actions (e.g., action, content, memory_id, query, category), but 22 total parameters exist, and many optional ones (auto, mode, as_of, depth, etc.) are not explained. The description adds value for the most common parameters but is incomplete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it is a legacy dispatcher for backward compatibility and lists all supported actions. It distinguishes itself from siblings by explicitly naming granular tools (e.g., add_memory, search_memory) and advising their use instead.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides an explicit 'ACTION GUIDE' detailing when to use each action (e.g., 'Use BEFORE add to avoid duplicates' for search) and includes a workflow (search -> not found? -> add). It also directs users to use specialized tools instead of this composite one.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true and destructiveHint=false, so the description adds value by specifying the exact statistics shown. It does not contradict annotations and provides useful behavioral context beyond the annotations alone.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise: two sentences plus a header. It front-loads the action and then provides usage conditions. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (0 parameters, read-only, output schema exists), the description is complete. It explains the tool's function and when to use it, and the output schema covers return values.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has zero parameters, so schema description coverage is 100% by default. The description logically adds no parameter information, which is appropriate. Baseline 4 for no parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Show database statistics (total memories, categories, embedding status).' It uses specific verbs and resources, and it distinguishes from siblings like list_memories which returns individual records.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description includes an explicit usage guide: 'Use when you need to understand the scale or health of the memory database, or check if embeddings are enabled.' This provides clear context, though it does not mention when NOT to use the tool or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate non-read-only and non-destructive. Description adds that it restores to 'active search pool' but lacks details on idempotency, error behavior, or preconditions. Adds some value beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Short, uses bullet list for guidance. No redundant sentences. Could be slightly more front-loaded but efficient overall.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output schema exists so return values not needed. Covers basic purpose and usage. Missing details like preconditions or error cases, but for a simple restore operation it is fairly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Single parameter 'memory_id' has 0% schema coverage. Description only gives an example value but does not explain format or constraints. Minimal addition over schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states verb 'restore' with resource 'archived memory' and method 'by ID'. Distinguishes from sibling tools like add_memory, delete_memory, etc.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says when to use ('bring a previously archived memory back into the active search pool') and provides an example. Missing explicit when-not-to-use or alternatives, 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.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, covering safety. Description adds that it uses natural language query and is for pre-addition search, but doesn't detail other behavioral aspects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with purpose and usage guidance, no wasted words. Every part earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 4 parameters and 0% schema description coverage, the description does not address parameter details or output structure (though output schema exists). Lacks completeness for a search tool with multiple optional fields.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

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 (e.g., tags, limit, category format). The only reference is to 'query' implicitly. Fails to compensate for minimal schema documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states 'Find existing memories by natural language query', specifying verb and resource. It distinguishes itself from siblings like add_memory by emphasizing search before adding.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly instructs to use 'BEFORE adding new information to avoid duplicates', with an example. Does not explicitly name alternatives but provides clear contextual guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=false (write) and destructiveHint=false (not destructive). The description adds that it modifies an existing memory and requires memory_id, providing useful behavioral context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, front-loaded, and includes a structured 'ACTION GUIDE' section. Every sentence is necessary and adds value without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema and good guidance on when to use, the description lacks detail on the meaning of optional parameters. For a tool with 6 parameters and 0% schema coverage, this leaves gaps for the agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but the description only mentions memory_id and content in the example, ignoring other parameters (tags, source, category, importance). It adds minimal meaning beyond the schema structure.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it modifies an existing memory by ID, distinguishing it from add_memory (create) and delete_memory. It provides an example and specifies that memory_id should come from search results.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states 'Use when an existing fact or preference changes' and instructs to get memory_id from search results, giving clear context for when to use this tool over alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.