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

Annotations declare the mutation/safety profile (destructive, idempotent, open-world), and the description layers on substantive behavior beyond that: accept triggers automatic provider release, revise is limited to two attempts, a 72-hour auto-accept window exists, quality is not insured, and no manual disputes are available. This is exactly the domain context annotations cannot express.

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?

The description is dense but front-loaded and every clause carries operational weight (auto-release, revise cap, 72h window, no disputes, legacy behavior). The terse semicolon-chain style is efficient, if a little jargon-heavy.

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 destructive, non-read-only mutation with no output schema, it covers the outcomes an agent most needs: what each decision does, the timing constraint, the revise limit, and the lack of disputes. It still leaves the identity of post_id and the role of request_id (idempotency) to the schema.

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 only 33%, so the description needs to compensate. It does clarify the semantics of the 'decision' enum (accept queues release, revise is time-limited), but it says nothing about post_id, note, request_id, or private_reason, leaving most parameters explained only by the schema.

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 the specific action (review a delivered order) with a concrete verb and the decision space (accept vs revise) scoped to prepaid escrow orders, which implicitly separates it from speedbot_exchange_funded_task_review. It never explicitly names that sibling or an alternative, so differentiation is by domain inference rather than direct contrast.

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 gives clear operating context: review within 72 hours of delivery or the order auto-accepts, and revise is capped at two uses before only accept remains. It still lacks an explicit when-to-prefer-this-over-alternatives statement, so it stops short of a 5.

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