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

The description adds substantial behavioral detail beyond the annotations: it discloses the PAID requirement and the in-band refusal for free keys, explains that a null fit indicates missing stored description, and mentions it returns the CV terms read. These details are not in the annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint) and enrich agent understanding. While it doesn't cover every edge case, it goes well beyond a bare statement, so a 4 is appropriate.

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 a single dense paragraph but every sentence contributes meaningful information: the core behavior, payment constraints, null semantics, and retry guidance. It is front-loaded with the primary purpose and then elaborates. Though somewhat long, it avoids fluff and is well-structured. It could be trimmed slightly but is not verbose, earning a 4.

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 tool has 6 parameters and an output schema, the description covers the core logic but leaves gaps. It explains the main flow (read occupation, search, score) and the output hints (null fit, returned terms), but does not clarify how optional parameters like remote, country, and location influence the search. The presence of an output schema reduces the need to describe return format, but the lack of explanation for these optional parameters, combined with their missing schema descriptions, makes the overall definition incomplete for an agent to confidently use all features. Thus a 3.

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 only 50% (limit and resumeText have descriptions; query, remote, country, location do not). The description clarifies resumeText (reads occupation from it) and query (alternative to resumeText), and implies limit (up to 20 results). However, it does not explain the remote, country, and location parameters at all, leaving them undocumented in both schema and description. Since the coverage is low and the description does not fully compensate for the missing parameters, a 3 is reasonable.

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 clearly states a specific action: 'Score a résumé against open jobs' and elaborates on the mechanism (reads occupation from resumeText or query, searches board, scores 0-100). This differentiates it from sibling tools like search or get_jobs by focusing on matching a CV to jobs, not merely retrieving or listing them. The verb 'score' and resource 'résumé against the board' are unambiguous.

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 provides clear context: it is intended 'for an agent holding a CV' and explains the prerequisite of a paid key or sign-in. It also implies a usage loop by stating it returns terms so the agent can retry with a query. However, it does not explicitly mention alternatives or when not to use it (e.g., when you just need a job list), though that is implicitly obvious from the purpose. This gives clear context without explicit exclusions, warranting a 4.

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