AI-Process Contract

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

With no annotations, the description discloses important behavior: only docContent/docName/IsAsync are sent, IsAsync must be true, the API returns 202 with a Location to poll, and the result is saved as process_contract.json. It does not cover errors or auth, but the core async behavior and side effect are clear.

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 dense and informative, front-loading the purpose and then giving params and async flow. There is minor redundancy/confusion around 'customFieldKeys or CustomFieldKeys', but overall it is well-structured for a tool with no output schema.

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 3 params, no annotations, and no output schema, the description covers the endpoint, the only params it sends, supported input formats, async behavior, and the saved output file. Missing output_dir semantics and return structure keep it from a 5.

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 description explains pdf_file_path (local file, formats, Base64) and doc_name (logical name, optional, defaults to basename), but says nothing about output_dir. Since schema coverage is 0%, this leaves one of three parameters undocumented, so it is useful but incomplete.

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 opens with 'extract structured data from a contract via PDF4me POST /api/v2/ProcessContract', which names a specific verb, resource, and target document type. This clearly distinguishes it from sibling process_* tools for invoices, receipts, and bank statements.

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?

It provides clear context: this is for contracts, takes a local file path, and uses an async polling flow. However, it does not explicitly say when not to use it or name alternatives like process_universal_document, so it misses the top tier.

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