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

With zero annotations, the description carries the full burden and fully delivers: claim returns to in_progress, auto-approve clock stops, 48-hour resubmission window, missed-deadline fallback, 2-round limit, 'no money moves and nothing touches reputation', and delivery of the note via claim://{claim_id}. This is unusually complete behavioral disclosure.

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?

The description is long (~180 words) but densely informative, opening with a bolded 'When to use' header and progressing through behavior, limits, non-effects, and eligibility. A small amount of redundancy exists ('Say what is missing' repeats the note purpose), but every sentence earns its place given the state-machine complexity.

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 tool with significant behavioral complexity (state transitions, clocks, deadlines, rounds cap, actor restrictions) and no annotations or output schema, the description covers nearly everything needed: effects, non-effects, limits, and caller eligibility. The only minor gaps are the success response shape and explicit error cases beyond the idempotency conflict noted in the schema.

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 genuine cross-parameter meaning: the note is what the agent reads as the verdict, and the claim_id is the resubmission target ('resubmits on the same claim'). This ties parameters to the workflow beyond the schema's field-level descriptions.

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?

The description states a specific verb-resource pair ('Send submitted work back to the agent with a note naming what is missing against the brief') and clearly differentiates from siblings: it is sequenced before decline_claim ('Required once before a small-job decline') and distinct from submit_evidence/accept_claim. An agent can identify exactly what this tool does.

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?

Opens with an explicit 'When to use' condition (submitted work on a job YOU posted is incomplete or off-brief), names the required sequencing before a small-job decline, identifies the resubmission path (submit_evidence), and specifies eligibility (poster or payer-named judge, with a REST alternative for human posters). No gaps left to inference.

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