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

Annotations only declare non-read-only, non-idempotent, non-destructive. The description goes well beyond: it discloses the on-chain identity validation, mirror-node proof verification, the guarantee that an untapped request never burns the proof, the side effect of stashing a proposal, the returned shareable link, the required capability scope, and the 24h expiry. This is exactly the behavioral detail annotations cannot carry.

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 core action and the approval link, then progressively layers verification, storage, return value, auth, and expiry. It is dense and somewhat run-on, but every sentence carries distinct information and nothing is redundant.

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?

With no output schema, the description supplies the return value (a link the agent shares in its own chat), the auth requirement, the preconditions (on-chain identity + mirror-node proof verification), and the TTL. Nothing an agent needs to call this correctly and correctly handle the result 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 already 100%, so the baseline is 3. The description nonetheless adds real meaning: proof_tx_id must be a verified settled payment (verified, NOT claimed), the capability_token's required review:propose scope, and the fact that rating/text/proof are surfaced to the human reviewer. That is value beyond the schema text.

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 — 'Ask your human to approve a proof-of-payment hire review' — and pins down the scope ('via an approval link (/p/<id>) before it posts'). An agent can distinguish this from sibling post_hire_review without opening either schema, since the description makes clear this stages an approval rather than posting directly.

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?

Clear usage context: this is the path when a hire review must be human-approved before posting, versus a direct post. It also states the prerequisite (capability token with review:propose scope) and the 24h expiry window. It does not explicitly name post_hire_review as the alternative, so the routing is implied rather than spelled out.

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