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

No annotations are provided, so the description must carry transparency. It clearly states that the tool is an estimate ('目安') and not official, and explicitly mentions the formula used ('厚労省のモデル年金と同じ式') and the output format ('月額・年額'). It also mentions the special mode for survivor pension and the parameters like 'mode=izoku' and '加給年金' and '在職老齢年金' – giving the agent insight into what the tool computes. It does not list limitations or edge cases, but the key behavioral trait (estimate, not official) is 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 moderately sized (about 150 characters) and front-loads the core purpose. It packs a lot of information but remains structured, with a clear progression from the main function to output details, to mode-specific behavior, to formula, and finally to use cases and caveats. It doesn't waste words, but the sentence is long and could be broken into clearer segments. That slight density prevents a 5.

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 (10 parameters, multiple modes, no output schema, no annotations), the description is fairly complete. It covers the main function, the special 'izoku' mode, the formula, the output details (monthly/yearly amounts, age adjustments, break-even, survivor pension), and the disclaimer about being an estimate. It doesn't explicitly describe the return format (e.g., JSON structure), but the description implies the outputs, and with no output schema, it would be helpful to mention that. Still, it's a strong effort.

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 10 parameters with 100% description coverage, so the baseline is 3. However, the description adds semantic information beyond the schema: it explains that 'nenshu' means average annual income including bonuses ('平均年収（賞与込み）'), and that 'kosei_years' is the number of years in the employee pension. It also gives defaults like 'claim_age' defaulting to 65 and 'kokumin_years' defaulting to 40, which the schema doesn't mention, adding value for the agent.

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 starts with a clear statement of what the tool does: '年金はいくらもらえるか（令和8年度）' (how much pension you receive), then elaborates with specific inputs and outputs. It distinguishes itself from siblings by naming alternative tools like 'tingin' (salary) and 'tedori' (take-home), and explicitly states when to use this tool for pension consultations. The verb '返す' (returns) indicates the tool's action.

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 lists the use cases: '年金はいくらもらえるか', '繰下げは得か', '遺族年金はいくら' (how much pension, is deferral worth it, how much survivor pension). It also provides clear exclusions: '目安であり、正式はねんきん定期便' (it's an estimate, official is the pension statement). This tells the agent when to use this tool and when not, and mentions the special 'mode=izoku' for survivor pension.

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