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

With no annotations, the description carries full burden and does well: it discloses that funds stay locked, that clear cases (no proof, unreachable proof) auto-resolve, and that contested work is adjudicated against the escrow description with a release-or-refund ruling. It omits whether a dispute can be withdrawn, whether rulings are final/appealable, and any timing windows before a dispute lapses.

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, and the highest-value facts are front-loaded: actor restriction first, then the funds/stakes consequence, then the adjudication path and the alternative tool.

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 no-annotation, no-output-schema mutation of financial state, the description covers stakes, adjudication criteria, and the preferred softer alternative. What remains thin is post-call behavior (how to track the dispute, expected timing) despite the get_dispute sibling existing for that purpose.

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?

Two parameters at 100% schema description coverage, so the schema already explains both escrowId and reason (including that reason is judged against the escrow description). The description adds no format, length, or evidentiary guidance beyond the schema, so baseline 3 applies.

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 ('dispute a submitted delivery') with an explicit actor constraint ('Buyer only'), which immediately separates it from seller-side siblings like release_escrow and submit_proof. An agent can pick this over request_revision or submit_evidence without opening another 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?

Names a real alternative and the condition that selects it: 'Consider request_revision first if the work is close.' Combined with the 'Buyer only' gating, the when-to-use case is clear, though no explicit when-not guidance (e.g., post-release or post-deadline situations) is given.

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