tokkyo-maru

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.

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

With no annotations, the description carries the full burden. It states the tool is deterministic and not a final legal determination, which is useful. However, it does not clarify if the tool is read-only or has side effects, and lacks information on authorization or rate limits.

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 relatively short but mixes Japanese and English, reducing clarity. It front-loads the purpose but lacks structured formatting. Every sentence adds some value, but the mixed language hinders conciseness.

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 complexity (7 parameters, no output schema) and lack of annotations, the description is incomplete. It does not explain the output format beyond ◯△✕, missing details on prerequisites, limitations, or how to interpret results. The disclaimer about legal finality is helpful but insufficient.

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%. The tool description only mentions passing 'tokkyo.json' without explaining the seven parameters. The meaning of fields like facts, category, priorArt, etc., is left to the schema's minimal description, which is insufficient.

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 specifies the tool checks novelty loss, description requirements, patent eligibility, and inventive step, outputting deterministic ◯△✕ judgments. It distinguishes itself as the patent version of houki_check, but does not explicitly differentiate from sibling tools tokkyo_analyze and tokkyo_draft.

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?

No explicit guidance on when to use this tool versus siblings. The description mentions it's the patent version of houki_check but does not provide context for when tokkyo_check is preferred over tokkyo_analyze or tokkyo_draft.

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?

No annotations are provided, so the description must carry full behavioral disclosure. It only states 'deterministically generate and return' and mentions tokkyo_check is included, but does not disclose any side effects, auth requirements, rate limits, or error behavior. The description is insufficient for an agent to understand implications.

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 (three sentences) and front-loaded with the core action. However, it lacks a structured breakdown and mixes output details with equivalence statements. Still, it is efficient and avoids verbose language.

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 12 parameters, no schema descriptions, no output schema, and no annotations, the description is incomplete. It fails to explain return structure, parameter constraints, or how inputs relate to the output. The agent lacks 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.

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 12 parameters (e.g., title, ipc, facts). The agent receives no guidance on parameter meaning or usage, making correct invocation difficult.

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 generates a patent specification skeleton from an invention, with specific output components (tokkyo.json, claims, description sections, abstract). It also references sibling tools to indicate similarity to other tools, establishing a clear identity.

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 does not provide explicit guidance on when to use this tool versus alternatives like tokkyo_analyze or tokkyo_check. It only mentions equivalence to other tools, leaving the agent to infer usage context.

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