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

Beyond the annotations it discloses the async contract (returns a run_id immediately, requires polling), the cost (50 credits), and the internal composition (CI_ANGEL, 5 agents). These are exactly the non-obvious behaviors an agent needs and are consistent with readOnlyHint=false and openWorldHint=true.

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?

Two dense sentences, front-loaded with the action and scope, followed by the operational follow-up and cost. Nothing is repeated or wasted.

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 swarm tool with no output schema, the description covers the return contract (run_id), the polling requirement, and the cost. Minor gaps remain around expected runtime and whether repeated calls spawn duplicate paid runs (idempotentHint=false).

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 50% and the description adds no guidance on what 'target' should contain or how to phrase it, nor on when supplying config.company_domain is worthwhile. Both parameters are at least partially documented in the schema, so the baseline of 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?

The description states a specific verb and resource ('Run an Angel Intelligence swarm') plus scope details (5 agents, pre-seed/seed startup triage, syndicate memo), so an agent knows exactly what the tool produces. It stops short of contrasting with the close sibling angel_deep_intelligence, so the depth/breadth distinction must be inferred.

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?

It clearly indicates the use case — early-stage startup triage — and prescribes the follow-up workflow ('poll check_report_status until completed'), which is the practical when-to-use guidance an agent needs. There are no explicit exclusions or 'use X instead' statements for the deeper angel or company intelligence siblings.

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