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

With no annotations, the description carries the full behavioral burden and does so thoroughly: it discloses data provenance and scale (about 20,000 company job boards), refresh cadence (crawled twice a day), a critical selection-bias caveat (only postings that publish pay), the return shape (p10/p25/median/p75/p90, typical range, remote vs on-site medians, top-paying companies, posting count), and the paid access model ($0.01 USDC on Base via x402). An agent knows both the economics and the reliability limits of the call before invoking it.

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 dense sentences that front-load the core purpose and then layer provenance, output fields and pricing in a logical order; almost nothing is wasted. The second sentence is a long run-on list but remains scannable.

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 four-parameter read tool with no output schema and no annotations, the description covers purpose, inputs, return fields, data source, freshness and cost, which is enough to call it correctly. It omits edge behavior — what is returned when a title matches no paid postings, or how title matching (exact vs. fuzzy) works — leaving a modest 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 description coverage is 100%, so every parameter is already documented in the input schema, including comma-separated title alternatives and the currency default. The description only summarizes 'Optional location, remote and currency' without adding format or matching semantics beyond the schema, which is the expected baseline when the schema does the heavy lifting.

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 opens with a specific verb-and-resource statement ('Salary for a job title: how much a role pays') and pins down the data source ('open postings that publish pay'), so an agent immediately knows this is an aggregated salary lookup rather than a listing search. It does not explicitly distinguish itself from the similarly named siblings jobs_search, jobs_new or company_jobs, so it stops short of a 5.

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?

Usage is only implied: the phrase 'Salary for a job title' tells an agent this is the pay-statistics tool, and 'from open postings that publish pay' hints at the coverage caveat. But there is no explicit when-to-use versus jobs_search or company_jobs, no statement of when not to use it, and no routing guidance for alternative tools.

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