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

Annotations already cover readOnly/non-destructive/closed-world, so the description's added value is provenance and recency: independent venues only (chains excluded), self-advertised pay rather than survey data, and a one-month window. That is exactly the kind of context annotations cannot convey. It stops short of caveats about sample size or what happens when only a handful of ads exist for a role.

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?

Two sentences, front-loaded with the substance and with no filler. The venue enumeration is slightly long but does real work by defining the population boundary; the parenthetical index citation is mild decoration.

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, so the description carries the burden of describing returns — and it does, naming median, range and ad volume. Combined with one optional parameter and full annotation coverage, the only gap is edge-case behavior for an unrecognized or sparse role.

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?

With a single parameter at 100% schema coverage, the schema already documents `role` as free-text with examples (barista, chef, kitchen porter) and the omit-for-all-roles default. The description only restates "by role" and adds no matching guidance, such as how to phrase a role that may not be indexed.

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 exactly what data comes back (median, range, ad count) for a precisely bounded population: hourly pay advertised by independent London cafés, restaurants, pubs, bars and bakeries on their own websites, this month. That scope definition cleanly separates it from the sibling job-listing tools (search_jobs, post_job, get_job), which deal with individual postings rather than aggregate market pay.

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?

"For an owner choosing what to pay, or someone weighing up a job" gives an implied audience and therefore an implied when-to-use, but there is no explicit routing: no when-not-to-use, no mention of alternatives, and no statement that this cannot answer questions about a specific vacancy (which is what the sibling tools are for).

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