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

The description discloses key behavioral traits beyond the annotations: it keeps the old record, marks it superseded, and does not delete anything (aligning with destructiveHint=false). It also explains the behavior when id is already superseded (reports replacement unless force=true). The annotations provide no contradiction; the description adds valuable context about side effects and edge cases. However, it does not mention error response details or permission requirements, which are not covered by annotations, but the core behavioral transparency is strong.

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 moderately long but every sentence serves a purpose. It is front-loaded with the primary action, then covers behavioral details, prerequisites, edge cases, and a sibling distinction. No filler or redundancy. It is well-structured as a single cohesive paragraph that reads naturally. Slightly longer than necessary but still efficient for the information density.

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 tool has no output schema, so the description must convey enough about behavior. It explains the non-destructive nature, the superseding mechanism, handling of already-superseded ids, and the prerequisite for id. It also differentiates from memex_store. For a mutation tool with 7 parameters (only 2 required), the description covers the critical aspects needed to use it correctly. It does not specify the exact response format, but it mentions 'reports the current replacement' which gives a hint. Overall, it is complete for the tool's complexity.

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 100%, so the baseline is 3. The description adds meaningful context for the key parameters: it emphasizes that 'id' must come from a prior result and that unknown ids are rejected (reinforcing but slightly extending the schema), and it clarifies the 'force' parameter by explaining the default behavior (reports replacement instead of writing) which is not fully explicit in the schema description. This adds value beyond the schema, justifying a score above baseline.

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 (correcting a wrong/outdated memory) and the mechanism (stores new text superseding an id). It clearly differentiates from the sibling memex_store by explicitly stating 'Do not use this for a brand-new, unrelated fact -- use memex_store instead.' This makes the tool's purpose unambiguous and distinguishes it from 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 description gives explicit when-to-use context (when a memory is wrong or outdated) and a direct exclusion ('Do not use this for a brand-new, unrelated fact') with the alternative named. It also states a prerequisite (id must come from a prior memex_recall or memex_get result, and unknown ids are rejected), which is critical for correct invocation. This is comprehensive guidance for selecting this tool over siblings.

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 annotations already declaring readOnlyHint=true, idempotentHint=true, and destructiveHint=false, the safety profile is covered. The description adds valuable behavioral context beyond the annotations: it specifies that unknown ids are errors, and it clarifies the verbatim returning of the memory and the correction chain traversal. This goes beyond the minimal requirement and earns a high score.

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 and front-loaded: the first sentence captures the core action, scope, and return value. Subsequent sentences provide usage routing. Every sentence contributes value; there is zero redundancy or fluff. This is a model of efficient, well-structured description.

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 fetch-by-id tool with one parameter, complete schema, and annotations, the description covers everything an agent needs: what it returns (verbatim memory and correction chain), how to use it (resolve superseded markers, confirm ids), error handling (unknown id is an error), and what it is not for (topic search, routed to memex_recall). No output schema is needed because the return value is described clearly. Nothing essential 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 single parameter 'id' has full schema coverage at 100%. The description adds critical semantic value by explaining that the id must be a valid record id and that unknown ids result in an error. It also implies the id is used for lookup, not filtering. Given the high coverage, the description's explicit error behavior and usage context fully compensate and exceed the baseline.

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 verb ('Fetch'), a specific resource ('exactly one memory by id'), and the exact scope (verbatim, with correction chain in both directions). It explicitly distinguishes itself from the sibling memex_recall by stating it is not for topic-based search. This is a clear, specific purpose that an agent can act on without ambiguity.

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 gives explicit when-to-use guidance: 'Use this to resolve a SUPERSEDED by <id> marker from memex_recall, or to confirm an id before passing it to memex_correct.' It also states an explicit when-not-to-use: 'Do not use this to find a memory by topic -- use memex_recall instead.' This is exemplary routing with clear conditions and named 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 already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered. The description adds valuable behavioral context beyond those annotations: the intended error-recovery sequence and the specific store-wide metrics included in the health check.

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?

Three sentences, each earning its place: the first states purpose and output content, the second gives usage context, and the third prevents misuse. No filler or repetition.

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 zero-parameter, read-only health-check tool, the description fully covers what it returns, when to call it, and when not to call it. No output schema exists, but the listed stats give enough expectation for an agent to interpret results.

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 zero parameters and 100% schema coverage, there is nothing for the description to add about individual parameters. The baseline for zero-parameter tools is 4, and the description provides no conflicting or redundant parameter information.

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 a specific verb ('Check') and a clear resource ('memory backend'), then lists exact stats the call returns (current/superseded/expired counts, oldest/newest record, queue/dead-letter depth). It explicitly differentiates from memex_recall by stating what this tool is not for.

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?

Provides unambiguous when-to-use guidance: call after any other memex_* tool returns isError, before retrying. It also gives a direct exclusion and names the alternative (memex_recall) for searching memory.

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, idempotentHint=true, and destructiveHint=false, establishing a safe read-only profile. The description adds valuable behavioral context beyond that: result ordering ('Current facts list first, superseded/expired after, marked'), the presence of id, status, and recorded date on each hit, and the mode-specific latency/behavior differences. It doesn't explicitly describe the historical flag's effect on ordering, but the schema covers its semantic, so a 4 is appropriate given the strong annotation coverage.

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 well-structured paragraph that front-loads the core purpose, then moves to usage guidance, then behavioral details, and finally alternative tools. Every sentence contributes new information; there is no fluff or repetition of schema content. The flow is logical and efficient.

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 5 parameters and no output schema, the description is remarkably complete. It explains when to call, how to choose modes, what the results look like (ordering, fields), and points to related tools for correcting or viewing history. The as_of parameter is documented in the schema, and the description doesn't need to repeat it. Nothing essential for an agent to use the tool correctly 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?

Schema coverage is 100%, so the baseline is 3. The description adds meaningful value beyond the schema: it explains the practical trade-off between fast and thorough modes with approximate latencies and when to choose each, and it clarifies the overall search semantics (hybrid search) not fully captured in the schema's enum descriptions. This lifts it to a 4.

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 verb and resource: 'Search stored memories for `query`.' It further specifies the use case (answering questions about prior work, decisions, or past conversations) and distinguishes itself from siblings by naming memex_correct, memex_get, and memex_store as alternatives for different actions. This leaves no ambiguity about what the tool does.

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 explicit when-to-use guidance: 'Call before answering questions about prior work, decisions, or past conversations.' It also gives nuanced usage instructions for the two modes, stating when to prefer thorough over fast ('only when a fast result looks wrong or stakes are high'), and explicitly warns not to use this tool for storing facts, pointing to memex_store instead. This is exemplary usage 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 establish read-only, idempotent, non-destructive behavior. The description adds meaningful behavioral detail beyond that: no search query is needed, `since` is a lower bound, and `kind=corrections` includes the IDs of replaced memories. It does not describe return shape or pagination, but for a simple list tool this is a minor gap.

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 the core purpose, and every sentence earns its place. It contains no filler, redundancy, or irrelevant detail.

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 read-only list tool with no required parameters, a complete input schema, and annotations covering the safety profile, this description is sufficient. It tells the agent when to use it, how the parameters behave, and which sibling to prefer for topic-based lookup.

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 100%, so the baseline is 3, but the description adds real semantics: it explains `since` as an ISO-8601 lower bound and clarifies that `kind=corrections` returns corrected memories with the IDs they replaced. This goes beyond the schema's basic descriptions.

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 lists memories by recency, names concrete use cases, and explicitly distinguishes it from memex_recall for topic search. This makes the tool's purpose unambiguous and differentiated from siblings.

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?

It provides positive guidance ('good for what changed recently or catching up after time away') and an explicit exclusion with an alternative: 'Do not use this to find a memory about a topic -- use memex_recall instead.' This is explicit when-to-use and when-not-to-use guidance.

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

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

The description explains behavior beyond the annotations: it states that unknown or another user's IDs are rejected, and it reveals the reply echoes recorded_at and any declared validity window so confirmation is possible without a recall. This gives the agent a clear picture of side effects and response characteristics beyond the raw annotation flags. No contradiction with the annotations exists.

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 but information-dense, with three sentences that each earn their place: purpose, optional parameters and response behavior, then an explicit exclusion. It front-loads the core action and verbatim requirement before details, making it easy for an agent to parse quickly.

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 write tool with one required parameter and a nested metadata object, the description covers what to do, when not to do it, what parameters matter, and what the response will contain. The nested relation declarations are already documented in the schema, so nothing essential is left for the agent to infer.

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 schema has 100% coverage, providing descriptions for all parameters, so the baseline is 3. The description adds valuable context, especially for supersedes by explaining that IDs must be valid and owned by the user, and for the temporal parameters by indicating they are optional and represent a validity window. It groups some optional parameters but does not add detail for metadata/relation declarations, which the schema already handles.

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 job: to remember or store one new, self-contained memory verbatim. It explicitly highlights that exact text should be stored, not a summary, and it distinguishes this from memex_correct in the closing sentence. An agent can immediately tell what resource this acts on and how it differs from its siblings.

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 says 'Do not use this to correct something already in memory -- use memex_correct with the old id instead of storing a near-duplicate,' giving both a when-not-to-use condition and the exact alternative. It also implies use for genuinely new memories by emphasizing 'one new, self-contained memory,' giving clear context for the expected use case.

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