Search filter values

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

The annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is fully covered by structured data. The description adds that this is a catalog of accepted values, but it does not say whether values come back as display labels or machine-usable slugs, nor whether they are static or live data, which is the actual behavioral unknown for a vocabulary tool.

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 short sentences, zero filler. The enumeration of facets is front-loaded, and the trigger condition follows immediately, so an agent can parse it in one pass.

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 zero-parameter, read-only catalog with no output schema, the description does the essential work: it says what the tool returns (the six accepted facets) and when to reach for it. It stops short of describing the shape of the returned values, which is the one thing an agent needs in order to map a rejected name back to a valid one.

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 tool accepts zero parameters, so the baseline of 4 applies. The description does usefully explain that the returned values are the accepted-vocabulary set the search consumes, which is semantically meaningful even though no parameter semantics are required.

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 uses a specific verb-plus-resource ("List every value the search accepts") and enumerates the facets it covers: provinces, categories, industries, experience, salary steps, and sort. This makes it clearly a reference/enumeration tool, distinct in kind from the search and detail siblings. It loses a point because it does not name the specific search sibling (jj_search_jobs) it feeds, so the pairing is only implied.

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?

"Use when a name is rejected" gives one concrete trigger and is genuinely useful, but nothing else: the description does not say to consult this before a first search, does not mention alternate cases such as validating user-supplied filters, and does not name sibling tools. The usage guidance is therefore implied rather than fully stated.

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