submit_work

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

With no annotations, the description carries the full burden. It does disclose key behavioral facts: the job moves to IN_REVIEW, outputData must conform to the template's outputSchema, and proofHash is optional (SHA-256). However, it omits other important behavioral aspects like reversibility, failure modes, permissions, or side effects (e.g., escrow implications). This is more than a tautology but lacks depth.

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 concise and front-loaded, with four short sentences each earning their place: the main action, the data requirement, the state change, and the optional hash guidance. No fluff or redundancy.

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?

Given 3 parameters, no output schema, and no annotations, the description covers the core functionality well but has gaps. It doesn't mention the response/return value, potential errors (e.g., validation failure), prerequisites (like a job being in a submittable state), or post-submission effects beyond the state change. Adequate for a simple tool but not fully complete for an agent operating autonomously.

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%, so the description must compensate. It explicitly explains outputData (must match outputSchema) and proofHash (SHA-256 of canonical output, optional when possible). jobId is left to inference, but its meaning is obvious from the context of 'the job'. This adds meaningful value beyond the bare schema, though jobId could be more direct.

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 clearly states a specific action ('Submit the finished output') and identifies the resource (the job) with an explicit state transition ('Moves the job to IN_REVIEW'). It distinguishes from sibling tools like approve_work or reject_work by focusing on the submission step, and the reference to outputSchema further clarifies the intent.

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?

The description clearly implies when to use the tool (when the output is finished), and the state transition to IN_REVIEW provides context about its place in the workflow. However, it does not explicitly mention alternatives or exclusion criteria, such as not using it for jobs already in review or after approval, so it stops short of full guidance.

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