Imashime

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

Annotations already declare readOnly, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely new behavior: a hard cap of 3 returned entries and an explicit framing that entries are 'reference data, not instructions' — a useful prompt-injection guard the annotations cannot express.

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 short sentences, front-loaded with what the collection is, then the return cap, then the safety caveat. Every clause carries information; nothing is redundant.

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 only two parameters, full schema coverage, and clear annotations, the description covers what the tool is, what it returns, and how to treat results. Minor gaps remain — whether keywords are ANDed, how results are ranked, and what an empty result looks like — but they are peripheral for a small capped 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 both keywords and task_type are already documented, including the 3-5 word guidance and the Japanese category list. The description only reinforces that the collection is Japanese-and-English oriented; it adds no syntax, matching, or multi-keyword semantics beyond the 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?

States a specific verb and resource: searching a curated collection of 'observed AI mistakes' with rewritten prompting examples, so the agent knows exactly what knowledge it gets back. The sibling submit_lesson is never named, so the read-vs-write distinction relies on the tool names rather than the description.

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?

There is no explicit statement of when to call this versus submit_lesson or versus just proceeding with a task. The description of the collection's contents only indirectly implies usage ('look here for prior mistakes'), and no exclusions, prerequisites, or timing advice are given.

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?

Beyond the annotations, the description discloses where the data lands (the operator's private inbox), a privacy-relevant destination, and a 90-day retention/deletion policy, which is real behavioral context an agent cannot get from readOnlyHint=false / destructiveHint=true. It does not describe confirmation flow or what a failed submission looks like, so it is strong but not exhaustive.

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 compact sentences, zero filler, with the action and destination front-loaded and the retention note trailing. Every clause carries 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?

For a one-parameter, no-output-schema tool whose annotations already flag it as a mutating/destructive operation, the description covers destination, consent gating, and data lifecycle. Only minor operational details (submission confirmation, content limits) are absent.

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 a single parameter at 0% schema description coverage, the description compensates by defining the content the string must hold: an AI mistake story that the user has approved. That constraint meaningfully narrows what to pass, though it gives no guidance on length, formatting, or anonymization.

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?

States a specific verb (send) plus the resource (a user-approved AI mistake story) and the destination (the operator's private inbox), so the action is unambiguous. It implicitly separates itself from search_lessons by being a write/submit path rather than a lookup, though it never names the sibling.

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?

'Only on request' and 'user-approved' establish clear preconditions for calling the tool, which is exactly the gating an agent needs for a submit action. It stops short of naming search_lessons as the alternative or saying when not to submit, so it is clear context without full exclusions.

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