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

Annotations only declare this is a safe, idempotent read; the description adds substantive behavior the annotations can't convey: the statistical shape of the return (median plus middle half), post-count disclosure, a coverage caveat the agent must relay verbatim, a hard minimum of 5 posts with fallback behavior (lists jobs that do have figures), and an instruction to pass on the `limits` field.

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 the triggering use case, then what is returned, then the caveats and the sub-5-post fallback. No sentence is filler: even the caveat about US-wide budgets and the `limits` passthrough change how the agent should phrase its answer.

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?

There is no output schema, and the description compensates fully by describing the return contents, the count disclosure, the link, the insufficient-data path, and the required caveat language. An agent can both call this correctly and relay its output accurately from the description alone.

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 100% and the single `job` parameter is already documented with examples such as 'lawn mowing' and 'tv mounting'. The description's examples are query phrasings rather than additional parameter constraints, so it adds little semantics beyond the schema; baseline 3 applies.

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 user scenario (someone who does the work asking what to charge) and precisely what comes back: the middle budget, the middle half of budgets, post count, and a link. It also draws a sharp semantic boundary against other price data ('not prices paid for finished jobs, not what any local earned'), though it never names the sibling check_job_price, so routing between the two still requires an inference.

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 opening 'Use this when someone who does the work asks what to charge' gives a clear triggering condition, reinforced by three realistic example utterances. It stops short of naming a when-not case or an explicit alternative tool (e.g. check_job_price for homeowner-side or paid-price questions), which would be needed for a 5.

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