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

Annotations already declare readOnly, non-destructive, closed-world, so the bar is lower; the description still adds real context about data provenance ('every price quoted from the company's own page with the date it was read') and the cost model used ('what three hires a year cost'), which tells the agent how figures were derived and how fresh they are. It stops short of describing the shape of the returned comparison or how ties/missing vendors are handled.

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?

It is one front-loaded sentence that immediately names the resource and the covered vendors, and the eight-brand list is genuinely useful for matching a user's mention to this tool. However, the comma-heavy run-on stacks several distinct ideas (coverage, pricing timing, cost model, provenance, audience) without structural separation.

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 one-parameter read-only tool with no output schema, the description covers what data is compared (published price, payment timing, annualized three-hire cost) and where it comes from. An agent has enough to call it correctly, though the response shape and handling of unavailable vendors remain unstated.

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 parameter's description already explains the default of omitting it, so the schema does the heavy lifting. The phrase 'each one's published price' hints that the default scope is all providers, but the description never explicitly mentions compare_with or its accept-one-value constraint, adding little beyond schema.

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 and resource — comparing hiring costs across named UK job boards and agencies — and enumerates the exact competitors covered, which lets an agent separate it from siblings like pay_rates or post_job without opening a schema.

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 closing phrase 'For an owner choosing where to advertise a job' gives an audience and implied context, but there is no explicit when-to-use, when-not-to-use, or named alternative (e.g., defer to pay_rates for salary data). Usage must be inferred.

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