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

Annotations already declare openWorldHint=true, readOnlyHint=false, and non-idempotent, and the description adds genuinely new behavior: the call is asynchronous, returns immediately with a run_id, and must be polled, plus it consumes 200 credits. It omits failure modes, expected runtime, and what happens to credits on failure, but the core operational profile beyond annotations is well covered.

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 sentences, front-loaded with the action, then the return/async contract, then the cost. Every clause carries actionable information with 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 an async, credit-consuming, non-read-only tool with no output schema and an undocumented nested config object, the description covers the run/poll lifecycle and cost but not what the report contains, how long it typically takes, or what config accepts. Adequate for invoking the tool, thin for using it confidently.

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?

With 50% schema coverage, the description must compensate, but it only loosely maps 'company or deal' to the target field, which the schema already documents in more detail. The config parameter is a free-form nested object with additionalProperties and no description in either the schema or the description, leaving a significant opaque input unaddressed.

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 a due-diligence (DD) swarm on a company or deal') and explicitly identifies it as an async job that returns a run_id. It does not distinguish itself from closely related siblings such as company_intelligence, angel_deep_intelligence, or sourced_brief, so an agent cannot tell from the text alone why it would pick this deep-research tool over those.

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 gives clear procedural guidance (poll check_report_status until completed) and a decision-relevant cost signal (200 credits), which is more than most definitions offer. However, it never states when to prefer this over the deeper/cheaper intelligence siblings, so tool selection still requires inference.

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