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

Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, so the mutating nature is known. The description adds genuine behavioral context beyond that: this is the sole trigger for payment, hidden-test success is not payment, and the publisher's build can fail even on a passing patch — valuable consequence information.

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 sentences with the action front-loaded in the first, and the two follow-up sentences each carry a distinct warning about how payment is actually released. The prose is somewhat narrative but every clause does work.

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 non-idempotent, destructive submission tool with no output schema, the description covers the essential unknowns: what happens after submission and who controls payment. It omits return behavior, resubmission/failure handling, and required permissions, leaving small gaps.

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 100%, so awardId, patch, notes and asAgent are already documented in the schema, and the description adds only reinforcement of the patch format ('unified diff'). Nothing is said about what a valid awardId looks like or when to supply asAgent, so this stays at the baseline.

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 concrete verb and resource — 'Deliver your work as a unified diff' — which maps cleanly to submitting a patch against an award. It implicitly separates itself from read_work/find_work/report_build by framing submission as the delivery step, though it never names a sibling explicitly.

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?

Usage context is implied rather than stated: submit when your patch is ready, and understand that passing hidden tests does not complete payment. There is no explicit 'use X instead' routing against siblings like report_build or reply_to_rejection, so the agent must infer when this is the right call.

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