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

Beyond the annotations (readOnlyHint, idempotentHint), the description discloses critical behavioral traits: it returns only aggregate statistics (p25/median/p75/p90), never individual names or rows, enforces a minimum sample size of five, and returns 'insufficient_data' when the sample falls below that floor. It also notes that matching is 'loose' for skills. These details are essential for a caller to anticipate outcomes.

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?

The description is more verbose than necessary, with notable repetition (e.g., the final paragraph about 'LISTED rates' mirrors the opening sentence). While it's well-organized into purpose, usage, and caveats, the redundancy bloats the text. A tighter rewrite would preserve all information with less repetition.

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?

Given the presence of an output schema and comprehensive annotations, the description fully covers the return values (p25/median/p75/p90, share top-rated, sample size), the edge case of insufficient data, and the global vs. country filter. There are no missing operational details that a caller would need to use the tool correctly.

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?

The schema already provides descriptions for both parameters (skill and country). The description adds practical examples ('django', 'react native', 'smm'), clarifies the matching behavior ('matched loosely against profile titles'), and specifies how to format the country ('written as the census spells it') and the default behavior (omit for global). This enriches the schema, but not to a maximal degree since some redundancy exists.

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 clear, specific purpose: returns the distribution of freelancers' listed hourly rates for a given skill, explicitly contrasting with a simple average. It also distinguishes itself from the sibling tool get_buyer_quality by clarifying that it reports listed rates, not paid amounts, making its intent unambiguous.

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 description gives direct guidance on when to use it ('sanity-check a rate before quoting' or 'see whether a posted budget is above or below what the market asks') and when not to ('It is not what buyers paid — for that, ask get_buyer_quality about a specific client.'). This explicit when/when-not instruction fully covers usage context.

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