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

Annotations only cover read-only/open-world hints, so the description carries the rest and does: it discloses result cap (up to 25), freshness semantics (re-read on a schedule, retired within ~36 hours of leaving), and the non-obvious rule that unposted pay is kept and ranked last rather than filtered out.

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?

Front-loaded with purpose and freshness, then inputs, then returns. Dense but every clause carries information; the long sentences slightly cost readability but not correctness.

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?

With no output schema, the description usefully enumerates what comes back (pay, asks, distance, last-confirmed time, apply link, job_id) and the 25-job cap, which is what an agent needs to plan. It omits any pagination behavior, which is the only real gap.

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 only 43%, so the description must compensate, and it does for the core fields (what/where/remote_only) and for filtering semantics. The enum-bearing params (radius_miles, employment_type, posted_within_days) are left to the schema, but their enums are self-describing.

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?

States a specific verb (search) and resource (live US jobs on employers' own careers sites), plus the defining scope: jobs live right now, re-read on a schedule, retired within ~36 hours. This cleanly separates it from siblings like get_job and is_job_still_open.

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?

Tells the agent what to supply ('what' and 'where', or remote_only) and clarifies the filtering contract: only the filters given are applied and the listed 'asks' are never used to drop a job. No explicit when-not or named alternative, but context is clear.

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