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

Annotations declare idempotentHint=false, yet the description states the call is 'exactly-once — a repeat release returns the existing terminal record, never a double payout', which is precisely idempotent behavior. An agent deciding whether a retry is safe would get two opposite answers from the structured field and the prose. The destructiveHint=true and openWorldHint=false claims are consistent, but the idempotency conflict is material.

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?

A single front-loaded sentence with the state precondition first and the safety guarantee in parentheses. No filler.

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?

An output schema exists, so return-value explanation is not required, and the destructive/monetary nature is stated. However, with two undocumented parameters and an idempotency signal that conflicts with annotations, an agent lacks enough to know how to supply delivery_proof or how to retry safely.

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 carry parameter meaning and it largely does not: it never explains that delivery_proof exists, what format it takes, or that it is presumably required when releasing a DISPUTED escrow. Only escrow_id is indirectly implied by the FUNDED/DISPUTED framing.

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 (release) and resource (escrow), plus the exact source states (FUNDED/DISPUTED) and the outcome (payee receives funds). That is enough for an agent to distinguish it from refund_escrow and dispute_escrow without opening any 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 FUNDED/DISPUTED precondition implies when the tool applies, but it never names the alternatives (refund_escrow, dispute_escrow) or the condition that selects them. Usage is inferable rather than stated.

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