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

With no annotations, the description bears full responsibility for behavioral disclosure. It transparently states the tool performs self-diagnosis with symbols and returns search angles/queries, and explicitly clarifies it does not file applications. This covers safety boundaries and limitations. However, it lacks details on rate limits, authentication, or whether it modifies any state.

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, consisting of two sentences that pack all essential information without fluff. It front-loads the core function and immediately follows with outputs and caveats. Every sentence adds value.

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 (11 parameters, no output schema), the description adequately covers the return structure (diagnosis marks, search angles, queries) and the tool's role (preliminary, not final). However, it could have elaborated on how outputs are structured or provided examples of the diagnostics. Still, it is largely complete for a diagnostic 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 description lists some key parameters (title, field, problem, solution, facts) corresponding to schema properties, adding context beyond their names. However, schema coverage is already high (91%), so the description adds limited additional meaning. Parameters like 'category', 'priorArt', 'claimCores', and 'disclosures' are not mentioned in the description, leaving some gaps.

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: pre-diagnosing patentability ('特許性を事前診断する') based on provided invention details. It specifies the output (IPC candidates, novelty loss, description requirements, etc.) and explicitly differentiates from siblings by noting it does not file applications ('代理出願はしない'), distinguishing it from tokkyo_draft. The verb 'diagnose' and resource 'patentability' are specific.

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 usage context: it is for pre-diagnosis and supports inventors/attorneys, not for final judgment ('最終判断は弁理士'). It states when not to use it (not a substitute for filing). However, it does not explicitly contrast with sibling tools tokkyo_check or tokkyo_draft, nor give detailed when-to-use vs. when-not-to-use scenarios.

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