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

Annotations already declare non-read-only, open-world, non-idempotent, non-destructive, but the description adds meaningful behavior beyond them: it is async, returns an investigationId immediately, degrades to info when unprovisioned, and requires operator authorization. The auth and degradation details are exactly the kind of context annotations cannot carry.

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 tight sentences with the action front-loaded, then preconditions, then the workflow handoff. No filler, and the most important routing information (start/poll/report) is stated compactly.

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 start tool with no output schema, the description covers the essentials: async semantics, immediate return value (investigationId), the poll/report workflow, and authorization prerequisites. The only real gap is parameter format guidance for query.

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?

There is a single parameter (query) at 0% schema coverage, so the description must compensate. Saying the investigation is 'for a domain' implies the query is a domain string, but the description never states the expected format, validation, or how the query relates to the maxLength 253 constraint. Baseline for the un-compensated gap is 3.

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 (Start) plus the resource (async OSINT investigation for a domain), and the 'for a domain' qualifier distinguishes it from the sibling osint_investigate_username_start/email_start/infrastructure_start tools without needing to open their schemas.

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 real selection context (operator-deploy only, targets must be operator-authorized on the recon watchlist) and routes the agent to the follow-up siblings osint_investigation_status and osint_investigation_report. It does not explicitly contrast against the other osint_investigate_*_start variants, so it stops just short of a full when-to-use map.

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