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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the description adds essentially nothing beyond that safety profile. It does not say what 'preview_search' actually does (does it persist a search?), how large result sets are, whether results are paginated, or what 'a changed search's matches' means. With annotations carrying the safety story, a 2 is fair for a description that adds no behavioral context.

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?

It is short in word count, but it is an unstructured run-on of noun phrases followed by a bolted-on 'Actions:' list and a help pointer. There is no front-loaded statement of purpose, and phrases like 'a changed search's matches' are opaque rather than concise.

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 multi-action, nested-parameter tool with no output schema, the description leaves too much unresolved: no per-action semantics, no return shapes, no note that 'help' is the intended discovery path until the last clause. The 'call help' convention is a reasonable design, but the description does not give the agent enough to choose an action confidently before that call.

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 action enum in the schema already lists all eight values, so listing them again in prose is repetition. The nested `params` object is an open-ended blob with no per-action property documentation, and the description responds only with 'call help' rather than compensating for the 67% coverage gap on a tool whose real parameters are hidden behind a runtime discovery step.

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?

It enumerates the resources reachable through the tool (matches, newest jobs, market map, company pages), so the domain is identifiable, but it never states what the tool does as a verb+resource and treats seven unrelated capabilities as one purpose. An agent cannot tell from the description how this differs from search_jobs or get_company_jobs, which sit right next to it in the sibling list.

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 action names are listed but there is no guidance on when to pick 'matches' versus 'preview_search', 'newest', or 'market_map', and no mention of when to use this instead of search_jobs/get_company_jobs. The only routing instruction is 'call help', which defers selection rather than explaining it.

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