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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds real substance on top: a role restriction (payee only), state preconditions (funded or submitted), and a specific failure mode (501 feature_unavailable when ESCROW_API_ENABLED is off). It does not say whether the refund is full or partial, or what the escrow state becomes afterwards, which keeps it from 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?

Three short sentences, zero filler, with the core action front-loaded and the preconditions and error mode following in order of importance. The parenthetical environment flag is the only mildly dense bit and it earns its place.

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 one-parameter mutation with no output schema, the description covers role, state preconditions, and a known error mode, which is most of what an agent needs. It leaves the return value and post-refund escrow state unstated, and with no output schema there is nothing else to fill that gap.

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?

There is one parameter (escrow_id) with 0% schema description coverage, so the description must carry the load. It only implies that escrow_id identifies the escrow whose state must be funded or submitted, adding no format, sourcing, or lookup guidance beyond that.

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?

"Refund an escrow to the payer" gives a specific verb and resource, and the phrase "gives the money back to the payer" makes the direction of funds unambiguous, which implicitly separates it from release_escrow. It stops short of explicitly naming release_escrow or dispute_escrow as the alternatives, so the sibling differentiation rests on inference.

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?

"Payee only, while funded or submitted" states both the caller role and the escrow-state preconditions, which is strong when-to-use guidance. There is no explicit when-not-to-use or pointer to the alternative tool for other states or roles.

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