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

No annotations are provided, so the description must carry the behavioral load. It does state 'Free, read-only,' which discloses the safety/cost profile, but it doesn't explain return formats, pagination behavior, rate limits, or what 'probes' means. For a multi-endpoint discovery tool with zero annotation coverage, this is only partially adequate.

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 packs multiple clauses separated by dashes and semicolons into one long sentence, which is dense and somewhat hard to parse on first read. It is front-loaded with the core purpose but the branching logic is buried in a run-on structure.

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 read-only discovery tool with no output schema, the description covers the main modes and endpoints, but it omits the 'limit' parameter semantics, return value shapes, and the meaning of 'probes' and 'ranked sellers'. Given the 33% schema coverage and no output schema, more completeness is warranted.

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 coverage is 33%, so two of the three parameters ('limit' and 'hireable') are undocumented in the schema. The description explains what 'class' and 'hireable' do functionally, but says nothing about 'limit' (the pagination cap of 1-200). It partially compensates for the low schema coverage but leaves the limit parameter unexplained.

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 states a specific verb ('Discover') and resource ('who can do a job') and then breaks down three distinct modes tied to parameters, each mapped to an endpoint. It is clear what the tool does, though some phrasing like 'the seller chooseSeller picks first, with its record and probes' is domain-specific and opaque without prior knowledge of the system.

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 effectively maps parameter combinations to outcomes: without 'class' returns job classes, with 'class' returns ranked sellers, and with 'hireable:true' returns hireable agents. This gives clear conditional guidance for when each mode applies, but it does not name sibling tools (e.g., taifoon_hire, taifoon_match) as alternatives or state when not to use this tool.

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