Save the public disclosure draft of my report

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

Annotations already mark destructiveHint=true and readOnlyHint=false, so the description is not required to state that this mutates state, but it adds the crucial specifics: it replaces the current draft, clears any approval, does not publish, and refuses published disclosures. This goes well beyond the annotations and explains exactly what destruction occurs.

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?

Four sentences with mostly high information density: purpose, eligibility, non-publishing caveat, and prerequisite are all covered. The final sentence 'they approve the old and new text' is a bit ambiguous, but the rest is well structured and front-loaded with the core purpose.

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 destructive mutation tool with eligibility constraints, approval semantics, and a two-party publication flow, the description covers everything an agent needs: what can be saved, what cannot, what changes, what does not change, and what to do first. The presence of an output schema means return-value details are not required, so nothing essential is missing.

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 documents all six parameters fully. The description adds some workflow context by mentioning the draft, revision, and the get_report prerequisite, but it does not meaningfully extend the meaning of the individual parameters beyond what the schema states. Baseline 3 is appropriate.

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 clear verb and resource: writes/saves the public disclosure draft (title, summary, write-up) of the researcher's own report, replacing the current draft. It also defines the eligible report state (fixed or closed, public programme, graded) and explicitly distinguishes saving from publishing, which clearly separates it from submit_report and update_report_status.

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?

Gives explicit when-to-use criteria: only for the signed-in researcher's own reports that are fixed/closed, on a public programme, and graded. It also states when not to use: published disclosures are refused, and saving never publishes. It prescribes the prerequisite action—read the draft and revision with get_report first—so an agent knows the correct workflow.

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