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

Annotations already establish destructiveHint=true and readOnlyHint=false, but the description adds substantial context beyond them: history is preserved, the original failure cause stays unknown, the server refuses in four named situations, the response contains only run status plus a committed closeout receipt, and the action is audited against the resolved member. It is only slightly short of full disclosure because it does not say what the caller should do if a refusal reason other than 'unconfirmed' 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?

Front-loaded with the action and the user-consent gate, then ordered into eligibility, auth, refusal conditions, response shape, and follow-up. Dense and mostly earned, though the credential/audit sentences are packed tightly enough that a reader must parse them twice.

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, and the description compensates by stating exactly what a successful response contains and how to handle an unconfirmed outcome (refresh and verify this same run before generating again). Nothing an agent needs to call it safely 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 coverage is 100%, so baseline is 3, but the description adds meaning the schema does not: the run id must be the exact run the user chose, and the request must be made under the same original initiating account and exact original delegated credential — which sharpens what on_behalf_of is really validating.

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 and resource ('Close one incomplete MIS generation') and immediately qualifies scope: only an eligible incomplete generation, only after explicit user choice. The outcome is spelled out ('permanently marks ... as failed while preserving its history'), so an agent can distinguish this from any generate or finalise sibling without reading further.

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 preconditions (user must explicitly choose to close that run; same initiating account, exact delegated credential, current Generate and entity access), explicit refusal conditions (capture committed, run busy, authority changed, safe closeout unprovable), and an explicit boundary against the alternative ('this tool never starts another generation'; ordinary Generate only after confirmed closeout).

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