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

Annotations cover the safety profile (non-read-only, open-world, non-idempotent, non-destructive), and the description adds real behavioral context beyond them: it is async, returns an investigationId immediately, requires operator deploy plus watchlist authorization, and degrades to 'info' when unprovisioned. It stops short of saying what happens on a duplicate start or what the async job does internally.

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 compact sentences, each earning its place: what it does, what gates it, and what it returns. The 'degrades to info when unprovisioned' clause is terse but load-bearing. Slight density risk, but 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?

No output schema exists, yet the description tells the agent the immediate return (investigationId) and the polling tool, plus deploy and authorization prerequisites. Complete enough to invoke correctly, though it omits failure modes for unauthorized or unprovisioned requests.

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 0% and the single 'query' parameter has no description in the schema, so the description must carry the burden — and it does by naming the accepted input types (domain, IP, org). It does not add format constraints beyond the schema's length bounds.

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 ('Start an async deep-infrastructure OSINT investigation'), the resource type, and the accepted query forms (domain, IP, org). This cleanly separates it from siblings like osint_investigate_username_start and osint_investigate_domain_start, which target narrower input types.

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?

Explicitly gives the follow-up path ('poll with osint_investigation_status') and states the deployment prerequisite and watchlist authorization requirement. It does not, however, explain when to prefer this broad infrastructure investigation over narrower siblings such as osint_investigate_domain_start or map_supply_chain.

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