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

Annotations already declare idempotentHint=true and destructiveHint=false, but the description adds material context beyond them: the required deliverable:write scope, the negative guarantee that storing a revise/reject request does not execute a revision, refund, recharge, reservation change or reward clawback, and that publishState only shares state/timestamp. These side-effect boundaries are exactly what an agent needs before calling a write tool.

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?

Five tight sentences, front-loaded with the action and choices, then prerequisites, then side-effect boundaries. Nothing is boilerplate, though the trailing MCP-client retention note is the least load-bearing sentence.

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 write tool with 0% schema coverage and no output schema, the description covers auth, idempotency, side-effect scope, and field-level meaning well. Gaps are the semantics of the `id` token and what happens if expectedRevision is stale, which a caller would want before committing a decision.

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 0%, so the description must compensate, and it largely does: it maps 'expected current revision and digests' to expectedRevision/originalFingerprint/deliveredDigest, calls out the idempotency key, explains reason as private and publishState as sharing state/timestamp only. The top-level `id` parameter and the revise-vs-reject conflict behavior remain unexplained, keeping it short of a 5.

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?

Specific verb ('Record') plus the exact resource (an acceptance decision on the original customer's retained delivery) and an enumeration of the three possible choices (Accept / Request revision / Reject). An agent can distinguish this from the sibling deliverable_acceptance_read without opening either 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?

The framing 'for the original customer's exact retained delivery' and the required revision/digest preconditions imply this is the write counterpart to deliverable_acceptance_read, but the description never explicitly states when to use this versus that sibling or when not to submit. Usage is inferred rather than stated.

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