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 well: it explains that the heat score combines applicant density with response reliability and is shrunk toward the platform average so a single lucky job cannot outrank a real market. It also tells the agent to read heat alongside confidence and previews the returned metrics, which goes well beyond the tool name.

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 tight and front-loaded: it opens with the core output metrics, then explains the ranking caveat, then gives the business use case and the sibling distinction. Every sentence contributes useful information and there is no filler.

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 read-only analytical tool with no annotations and no output schema, this is close to sufficient: it names the returned metrics, the heat-score behavior, and the main use case, while the schema covers filters and limits. The exact time window and precise machine-readable output field names are left implicit, so an agent may still need to infer some response structure.

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 input schema already describes all four parameters at 100% coverage, so the baseline is 3. The description adds meaning beyond the schema by explaining what heat and confidence represent and implying that heat is the default ranking score, while leaving limit, state, and minJobs to the schema's own descriptions.

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 'Find which US cities are actually converting' and then lists the concrete metrics: jobs posted, locals applied, reply share, and median hours to first applicant. This gives a specific verb, resource, and measurable outcome, and the closing complement comparison distinguishes it from the worker-counting service-availability tool.

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 explicitly says to use this tool to decide where supply is dense versus where jobs go unanswered, which is a clear trigger. It also names get_service_availability as the alternative and contrasts measuring response with counting workers, though the sibling list shows check_service_availability, so the routing is slightly inconsistent.

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