compare_companies

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

With no annotations, the description carries the behavioral burden. It discloses a key behavior: partial failure isolation ('One company failing does not lose the others; each failure is reported beside the results that did work') and normalization of field names across systems ('Companies on different systems come back with the same field names'). This provides valuable behavioral context beyond the schema. It does not cover every possible behavior (e.g., auth, rate limits), but the core transparency is commendable.

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 somewhat verbose and literary, with phrases like 'This is the thing no single applicant-tracking system can do' and 'each vendor only knows about its own customers' which add flavor but no operational value. The core information (multi-company, normalized fields, failure isolation) is present but could be stated more tersely. It's not overly long, but it has noticeable fluff, so a mid score is warranted.

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 there is no output schema, the description should explain what the agent can expect as a result. It mentions that field names are unified and failures are reported side-by-side, but it does not describe the actual return structure (e.g., array of company results, status codes, error format). For a tool with two parameters and no output schema, this is a moderate gap. The tool is otherwise reasonably well-specified, so a 3 is fitting.

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% — both 'companies' and 'per_company' already have descriptions in the schema. The tool description does not add any additional meaning or syntax details beyond what the schema provides (e.g., it doesn't clarify URL formats or constraints further). With full coverage, a baseline of 3 is appropriate.

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 clear verb+resource: 'Open jobs across several companies at once, in one schema.' It explicitly differentiates from single-company ATS tools by highlighting cross-system comparison, which distinguishes it from siblings like list_open_jobs or find_company_board. The purpose is unambiguous and not just a restatement of the name.

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 implies usage for multi-company comparison ('Open jobs across several companies at once') and notes it's 'the thing no single applicant-tracking system can do,' which suggests when to use it. However, it does not explicitly name alternatives or state when not to use it (e.g., for a single company, use list_open_jobs). The guidance is implied, not explicit.

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