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

Annotations declare non-read-only, open-world, non-idempotent, non-destructive, and the description adds key behavior beyond them: per-domain run creation, a 100-target cap, immediate 202 response, and polling via enrichment_runs-get/list. Missing permission/cost details, but strong operational disclosure.

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?

Four sentences, front-loaded with purpose and scope; each sentence carries operational information about cap, async behavior, or polling. 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 complex asynchronous batch write with rich schema and annotations but no output schema, the description supplies the needed execution model: cap, 202, and how to retrieve runs. It could mention auth/credit implications, but core call-completeness is adequate.

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 coverage is high, so the schema documents most fields. Description adds batch semantics by tying the question to all targets and reinforcing the 100-target limit from the schema, though it does not explain the many other optional configuration parameters.

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 'Enrich' and resource 'companies' with batch scope 'many' and 'one shared custom question,' distinguishing it from the single-company sibling companies-enrich_custom. An agent can identify batch custom enrichment immediately.

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?

Explains the batching context: use when enriching many companies with one shared custom question, and split larger lists into calls of 100 or fewer. It also directs polling after the call, though it does not explicitly name companies-enrich_custom as the single-company alternative.

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