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

The '読み取り専用' tag merely repeats readOnlyHint=true and earns no credit, but the description does disclose behavior the annotations cannot: the data is derived from currently-listed postings, it is aggregated (count plus min/median/max), and values are in 万円. That is meaningful context for interpreting results, though it says nothing about caching, update frequency, or what happens with a sparse sample.

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?

A single dense sentence that front-loads the resource (職種 × 都道府県の年収相場) before the returned metrics. Efficient, but the trailing parenthetical repeats the read-only hint already carried by annotations, which is mild waste in an otherwise tight sentence.

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 no output schema, the description usefully enumerates the returned fields (posting count, min/median/max, unit 万円), which is what an agent needs to use the result. Annotations cover the safety profile. Remaining gaps are minor: no note on returned shape when prefecture is omitted or on thin-data behavior.

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 schema already documents both parameters, including that prefecture is optional and that occupation requires an exact canonical match. The description only restates the occupation × prefecture key, adding no format or matching semantics beyond the schema. Baseline 3 applies.

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 precise verb+resource: returns annual-salary market data (posting count, min/median/max offered salary) keyed by occupation × prefecture. That clearly separates it from the job-listing siblings, but it never names job_search/job_detail as alternatives, so differentiation is inferred rather than stated.

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?

Usage is implied by the aggregation framing ('掲載中求人の…求人数・提示年収'): you call it when you want salary benchmarks rather than individual postings. There is no explicit when-to-use statement, no exclusion of cases where job_search would be the better call, and no prerequisites mentioned.

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