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

Rich disclosure beyond the annotations: it states the mcp:report scope requirement, the lease-binding validation rule, the append semantics ('once per lease'), and, importantly, that the record is evidence of the agent's own claim and not proof of enforcement nor an authorization. The one soft spot is tension with readOnlyHint=true — the description says the outcome is 'Recorded as evidence', which is a persistent write to the server's record set, and the text does not reconcile that with the read-only annotation (nor explain what happens if the report is rejected).

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?

Front-loaded with the call-timing clause, then constraints, then caveats — a sensible order with no filler. It is dense to the point of being a run-on, cramming scope, lease validation, evidence semantics, and a non-authorization disclaimer into two long sentences, though each clause carries real information.

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 a 5-parameter sequencing-dependent reporting tool with no output schema, the description supplies what an agent most needs: when to call, auth scope, lease binding, and what the record does and does not mean. Gaps are minor — failure/rejection behavior, retry after a rejected report, and the 'run' parameter are left to the schema.

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 100%, so the schema already explains every parameter, including the 'identifier only, never content' rule for external_ref. The description reinforces the lease/intended_action binding and the once-per-lease constraint, but adds no new syntax, format, or edge-case meaning, and never mentions the 'run' parameter or its shared-installation requirement.

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 names a specific verb and resource (report the outcome of an action you already took) and pins its exact position in the lifecycle: "Call AFTER acting on an allow from verify_premises, once per lease." That distinguishes it cleanly from the siblings verify_premises (authorizes), check_premises (checks), and report_agent_run (run-level reporting), so an agent can pick it without opening any schema.

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?

Timing is explicit (after acting, once per lease) and the eligibility condition is explicit (only for a lease this same connection used in verify_premises, with the same intended_action). The three permitted outcome values are restated as the decision an agent is making, which tells the agent exactly what state it is in when it should call this.

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