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

With no annotations, the description carries the full burden and does real work: it discloses side-effect boundaries ('No fee is purchased, no delivery approved, and no money moves'), auth requirements ('Requires API key'), and the evidence-sharing gate on invitations. It doesn't address revoke semantics, idempotency, or what state a receipt enters after a verdict, so not a 5.

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 dense sentences, front-loaded with the action set and actor roles, followed by the safety and auth caveats. No filler; every clause adds either scope, a constraint, or a side-effect disclaimer.

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?

This is a complex three-branch, multi-parameter tool with no output schema and no annotations, so the description must do substantial lifting. It covers roles, gates, and side effects well, but omits what submit returns, the purpose of expected_receipt_version, and revoke/decline consequences — gaps an agent will notice at call time.

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 reported at 100%, so the structural contract is documented. The description adds semantic weight only for no_conflict_declared ('never declare no conflict unless true') and for the evidence-sharing approval. It leaves verdict enum values, the meaning of limitations, and especially expected_receipt_version (clearly a concurrency check) unexplained.

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 all four operations distinctly (invite a reviewer, submit a verdict, decline, revoke) against a specific resource (a frozen delivery receipt) and assigns each an actor role (buyer vs. invited reviewer). It is clearly separable from siblings like list_independent_reviews or save_delivery_receipt. Sibling-differentiation is implicit via role, not explicit.

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?

It states the precondition for invite ('requires explicit evidence-sharing approval') and attributes each action to the correct actor ('as invited reviewer', 'as buyer'). The 'Never declare no conflict unless true' line is a genuine usage constraint. It does not explicitly name alternatives, but the when-to-use context per action is clear.

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