process_agent

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so well. It explains the execution flow: reads the file from disk, uploads as multipart/form-data, waits for the result, and returns extracted data directly. It also discloses the economic side effect: credits are deducted and refunded on failure. This gives the agent a clear model of what happens when the tool is invoked.

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, each earning its place: the first states the core operation, the second summarizes the execution mechanics, and the third clarifies the return model and billing behavior. The most important differentiator (synchronous, no polling) is front-loaded, making the tool easy to classify quickly.

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 5 parameters, no annotations, and no output schema, the description provides essential context: synchronous execution, file read behavior, upload mechanism, direct return, and credit handling. It could additionally mention failure modes, file size limits, or authentication requirements, but the core behavioral and selection information an agent needs is present.

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?

The input schema already provides 100% parameter description coverage, so the baseline is 3. The description itself does not add much per-parameter meaning beyond what the schema states; it mainly adds context about the overall synchronous behavior. It does clarify that prompt_json acts as the extraction schema, which slightly reinforces the schema, but the schema already communicates this.

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 ('Submit'), a specific resource ('a document for SYNCHRONOUS agentic extraction via DocuProx'), and clearly distinguishes itself from sibling job-polling tools by saying 'Returns the extracted data directly (no job polling needed)'. An agent can immediately tell this is the synchronous, direct-result path rather than process_job, job_status, job_results, or poll_job.

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 gives clear context for when to use this tool: for synchronous extraction where the result is returned directly, with no polling. It implicitly contrasts with the async job-based siblings by explicitly saying 'no job polling needed', which helps an agent choose between this and process_job/poll_job. However, it does not explicitly name the alternative for async use cases or state exclusions.

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