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

Annotations already declare destructive=true, readOnly=false, non-idempotent and open-world, but the description adds substantial context beyond them: accept publishes the escrow.release outbox event and creates worker_payouts, reject opens a disputes row, request_changes returns the task to in_progress, archives the superseded proof, extends the deadline, and caps resubmission at two attempts.

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?

Front-loaded with the decision enum, then structured into three consequence-focused paragraphs. It is dense with URLs and error codes but nearly every sentence carries decision-relevant information, so little is wasted.

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 destructive, multi-outcome decision tool with no output schema, the description covers consequences, error conditions (409), limits (max two change requests), and downstream alternatives. An agent has everything needed to choose correctly.

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 coverage is 100%, so the baseline is 3, but the description adds meaning: it explains the consequence tied to each decision value and notes that reason is required for both reject and request_changes and is read by a person. The two-attempt cap adds decision-relevant context not fully captured by the schema alone.

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 (review/submit decision) and resource (submitted completion proof), and enumerates the three valid decisions. It clearly distinguishes itself from read-oriented siblings like get_task_proof by describing the side effects of each decision.

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?

Explicitly names when to use request_changes vs reject ('incomplete or ambiguous rather than wrong'), states it is the right call far more often, and routes the reject path to the alternative POST /v1/ops/disputes/{id}/resolve endpoint. The 409 change_request_limit_reached limit is also disclosed.

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