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

Annotations already declare readOnlyHint=true and openWorldHint=false, so no destructive or open-world behavior is expected. The description adds valuable non-obvious behavior: data comes from the ShearQuery directory, coverage is deepest in Houston and thinner elsewhere, and city results with fewer than 5 reported rates return a count without a median. These caveats are materially useful for interpreting results.

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 dense and front-loaded with the main operation, followed by data-source context and edge-case behavior. The final explanatory clause is slightly wordy but earns its place by clarifying why sparse data is handled differently. No filler or redundant restatement of the title.

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 that there is no output schema, the description does a good job enumerating the returned metrics and explaining threshold and omission behavior. The optional parameters are fully covered by the schema PARA. The only minor gap is that it doesn't describe the exact response structure or explicitly routing to alternatives, but neither is essential for this tool.

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?

All three parameters (city, type, examples) have full descriptions in the schema, so the baseline is 3. The description reinforces the city-omission behavior and the 'with a published rate' qualifier for examples, but it doesn't substantially add semantic meaning beyond what the schema already provides.

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 verb and resource: 'Return what barbershops and salons in a city actually charge for a chair or suite' and enumerates the metrics (median weekly rent, range, venue counts, chairs, hiring). This distinguishes it from siblings like compare_barbershops_salons and compare_barber_cosmetology_schools, which focus on comparisons rather than actual city-level rent benchmarks.

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?

It gives clear context for how to invoke different behaviors: include a city for local figures, omit it for the overall picture and cities with the most reported rates, and be aware that fewer than 5 reports suppress the median. It never explicitly names a sibling as the alternative, so it stops short of a 5, but the usage context is more than implied.

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