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

Annotations only say destructiveHint=true and readOnlyHint=false; the description adds substantially more: the payee receives the amount less fee_bps, the result is 'pending while the payee's payout delay runs,' and the call returns 501 feature_unavailable when ESCROW_API_ENABLED is off. Authorization scope (payer only) is also disclosed, which annotations do not cover.

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?

Three tight sentences, front-loaded with the action, followed by the authorization/state guard and the feature-flag failure mode. No filler, and each clause carries operational information.

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 single-parameter mutation with no output schema, the description covers authorization, state preconditions, the payout outcome and its pending state, and a known error path. The main omission is what the caller receives back (transaction or escrow identifier, resulting status) beyond the prose description of effects.

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% and there is one parameter, escrow_id, that the description never characterizes — no format, no source of the value (e.g., from list_escrows or get_escrow), no error behavior for a bad id. The only signal is the generic word 'escrow', so the description does not compensate for the coverage gap.

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 ('Release an escrow') plus the direction of funds ('to the payee'), which implicitly separates it from refund_escrow and dispute_escrow in the sibling list. It does not explicitly name those alternatives, so the differentiation is inferable rather than stated.

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?

Gives clear preconditions: 'Payer only, while funded or submitted,' telling the agent who may call it and in which escrow states. It stops short of naming sibling alternatives (refund_escrow, dispute_escrow, cancel_task) or stating when release is inappropriate, but the state guard is real guidance.

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