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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuine context beyond that: jobs are expected to be long-running ('a grid search works through many map points, and enrichment fetches every website in the batch'), which tells the agent not to treat slowness as failure. It stops short of describing terminal states, failure modes, or progress reporting.

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?

Three tight sentences with zero filler: the set of originating tools is front-loaded, the call mechanics follow, and the long-duration caveat closes. Every sentence earns its place.

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 polling tool with no output schema, the description never says what the returned status looks like or, critically, that completed results are retrieved via siblings like get_search_results or list_results. The kind enum and the long-job expectation are well covered, but the post-completion path is missing.

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% and the enum's own description already maps each kind to its originating tool, including enroll_leads under "enrich". The description's "pass the job id and its kind" and the tool-to-kind mapping largely restate the schema, adding only marginal emphasis. Baseline 3 is appropriate.

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?

States a specific verb (poll) and resource (background job) and names exactly which sibling tools create the jobs it polls (search_areas, enrich_leads, enroll_leads, find_contacts, verify_emails). An agent can distinguish this from result-fetching siblings like get_search_results without opening any schema.

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?

Clearly establishes the usage context: call this after one of the named tools starts a background job, passing its job id and kind. It does not, however, say when to stop polling or route the agent onward to result tools (get_search_results, list_results) once the job completes, nor mention polling cadence.

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