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

Annotations only say readOnlyHint=false and destructiveHint=false. The description adds genuinely useful context beyond that: idempotency scoped to the same session_id, retry safety, and an auth requirement. It is missing only the failure/partial-success semantics of a multi-effect operation (e.g. what happens if the wallet mint succeeds but the SEO mirror write fails).

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 sentences, zero filler, front-loaded action and effects before the idempotency and auth notes. Every clause carries information the agent needs.

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?

There is no output schema, and the description compensates by naming the return payload fields (capabilities, operator_id, discovery_url). Combined with the auth-required and idempotency notes, an agent has enough to invoke this 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?

With one parameter at 100% schema coverage the baseline is 3, but the description adds meaning by tying the session_id to pcc_onboard_session_start and by scoping idempotency ('safe to retry inside the same session_id'), telling the agent what reuse of the same id does.

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 ('finalise') with the resource (physical-operator onboarding session) and enumerates the concrete effects: registers the operator on PCC, mints a wallet, writes the SEO mirror, and returns the publication payload. This clearly separates it from siblings like pcc_onboard_session_start, _status, _ingest_docs, and _scrape.

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?

'Finalise' plus the session_id parameter documented as 'returned by pcc_onboard_session_start' makes it clear this is the terminal step of the onboarding sequence. It gives no explicit when-not-to-use or alternative guidance, but the position in the flow is unambiguous.

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