Discover more brand names

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

Annotations only mark it non-read-only, open-world and non-idempotent; the description adds the async background-job model, the mandatory polling step, and the crucial replacement semantics ('passing the full list including the names already there'), which prevents an agent from dropping existing aliases. It also discloses what shoppingEnabled and country actually change about the search.

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?

A single dense paragraph, front-loaded with what the job finds and immediately followed by the exclusion and the follow-up flow. Every clause earns its place, though the trailing shoppingEnabled/country sentence could be split for readability.

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 async job with no output schema and sparse parameter documentation, the description covers everything an agent needs: what is produced, how to retrieve it, how to present it, and how to persist it without clobbering existing data.

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 only 20%, so the description must carry the load and largely does: it explains shoppingEnabled (adds Google Shopping), country (narrows to one market, ISO 3166-1 alpha-2), and the competitorId used downstream. requestId's idempotency semantics come from the schema itself, and organizationId/projectId are self-evident, so the gap is minor.

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 and resource: 'Start a background job that finds other names the project's brand and each of its existing competitors go by in AI answers and search results (aliases, product and store names).' It also draws an explicit boundary — 'It does not find new competitors' — which separates it from siblings like create_competitor and discover_keywords.

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?

Gives an explicit end-to-end workflow: poll get_job for the result, show it to the user, then add chosen names with update_project (brand) or update_competitor (competitor, by competitorId). The 'does not find new competitors' exclusion plus the named follow-up tools leave nothing to inference.

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