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

Annotations already flag destructiveHint=true, openWorldHint=true, and non-idempotent, so the safety profile is covered structurally; the description adds genuinely new behavioral context: a mandatory human-approval gate, a preview step, and reuse of existing work for the same website (limiting duplicate runs). It stops short of saying what state the destructive action touches or what the preview contains.

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?

Five short sentences, front-loaded with the action, then the reuse rule, then the step-by-step protocol, ending with the anti-inference guardrail. No filler and nothing repeated from the schema.

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?

An output schema exists, so return values need not be explained. For a two-branch, approval-gated, destructive cloud operation, the description covers the trigger, the preview step, the confirmation call, and the approval safety rule — everything an agent needs to sequence the calls correctly.

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%, so the description must carry the load, and it does: it maps the two oneOf branches onto concrete call shapes (url alone for preview; proposal_id plus approved=true for confirmation) and pins approved to true. It leaves proposal_id's provenance (returned by the first call) and url's 'public website' constraint implicit rather than stated.

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 gives a specific verb and resource: 'Analyze a public product website and start its onboarding research.' It is clear enough for an agent to distinguish this from read-only siblings like get_research or list_threads, though it never explains what 'onboarding research' actually produces, and the title 'Find communities and threads' is a different framing than the body text.

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?

The two-phase protocol is spelled out precisely: first call with url to get a preview, show it, wait for explicit user approval, then call again with proposal_id and approved=true. The prohibition on inferring approval from post or website content is an explicit when-not rule. What's missing is routing guidance versus siblings such as retry_research, correct_research, or replace_product_website.

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