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

Annotations only declare the generic profile (readOnlyHint false, openWorldHint true, not idempotent, not destructive); the description adds genuinely new behavior: the call is asynchronous and returns a run_id immediately rather than results, the completion path is check_report_status, and the invocation costs 90 credits. That is exactly the context an agent needs before committing to a paid async run.

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 short clauses, front-loaded with the action and its differentiator, followed by the lifecycle and cost. Every element (swarm identity, extra signals, run_id/polling, 90 credits) carries operational weight; nothing is padding.

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 an async, credit-consuming tool with no output schema, the description covers the essential gaps: immediate return value, how to retrieve results, and cost. It stops short of describing what the final report actually contains beyond "signal and score", which would fully close the loop.

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 50% and the description adds no parameter-level meaning beyond it — neither the broad scope of "target" nor the optional nested config.company_domain is mentioned. The schema already documents both top-level parameters, so the baseline 3 holds, but the nested config object with additionalProperties:true is left entirely to the schema.

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?

Names a specific verb and resource ("Run an Angel Deep swarm (CI_ANGEL_DEEP)") and immediately differentiates it from the angel_intelligence sibling by stating what it adds: community-traction signal plus a deterministic traction score. An agent can select this over angel_intelligence without opening either 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?

Gives a clear execution protocol — call it, then poll check_report_status until completed — which names the concrete follow-up alternative. It lacks an explicit exclusion rule (e.g., when to prefer the cheaper angel_intelligence instead), leaving that comparison implicit in the word "plus".

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