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

Goes well beyond the annotations by disclosing the downstream effect (operator queue), the follow-up endpoints (GET /disputes/{id}, POST /disputes/{id}/respond), a monetary consequence (loser pays the $5 dispute fee), a permission prerequisite, and a feature-flag failure mode. None of that is derivable from readOnlyHint=false / destructiveHint=false.

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?

Short and front-loaded: action first, then eligibility, then consequences and failure mode. The parenthetical endpoint paths are slightly extraneous for an agent invoking the tool, and the elliptical fragment "Payer or payee, once something was submitted" reads awkwardly.

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 two-required-param mutation with no output schema and no annotations about outcomes, it covers eligibility, cost, routing and the disabled-feature error. What is missing is the parameter-level guidance and any hint about what the call returns (e.g. a dispute id to poll).

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% with three params, so the description carries full burden, yet it says nothing about escrow_id format, what belongs in reason, or the difference between reason and the optional evidence. An agent must guess at the content of the two free-text fields.

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+resource ("Dispute a submitted escrow") and constrains the actor and timing ("Payer or payee, once something was submitted"). It does not explicitly distinguish itself from the sibling file_dispute or explain the escrow-vs-task boundary, so an agent must infer the split.

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 concrete eligibility conditions: only payer or payee, only after something has been submitted, and requires the can_open_disputes permission. It also notes the 501 feature_unavailable behavior when stand-alone escrow is disabled, which prevents wasted calls. No explicit pointer to when a different sibling (e.g. file_dispute) is preferred.

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