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

Beyond the annotations (readOnly=false, idempotent=true, destructive=false, openWorld=false) the description adds the authorization requirement, the privacy split between a private reason and publishState sharing state/timestamp only, the explicit non-effects on refunds, reservations and rewards, and the retry semantics of the idempotency key. These are exactly the side-effect facts an agent needs before mutating acceptance state.

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?

Sentences are front-loaded and each carries content: action, preconditions, privacy, non-effects. It is dense and slightly run-on, and the trailing note about the MCP client retaining private messages is a marginal caveat, but nothing is padding.

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 nested-object mutation with no output schema, the description covers auth, concurrency preconditions, idempotency, privacy and absence of downstream side effects. It does not describe what a successful response looks like or what happens on a refused stale revision, leaving a small gap that a reader of deliverable_acceptance_read would have to fill.

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 choice, reason, publishState, idempotencyKey, expectedRevision, deliveredDigest and originalFingerprint. The description restates the privacy behavior of reason/publishState and gestures at revision/digest currency, but adds little syntax or constraint detail beyond the schema, so the baseline 3 applies.

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 opens with a specific verb-and-resource statement: record accept/revise/reject for the original customer's exact retained delivery. That is far more than a restatement of the name and makes the write-vs-read split against deliverable_acceptance_read inferable, though the sibling is never named outright.

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?

Preconditions are spelled out (explicit deliverable:write, expected current revision/digests, idempotency key), and the description scopes the tool negatively by stating that request storage does not execute revisions/refunds, recharges, reservation changes or reward clawbacks. What is missing is an explicit pointer to deliverable_acceptance_read as the step that produces the revision and digests, so the agent must infer the workflow order.

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