AI-Process Mortgage Document

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

Even though no annotations are provided, the description discloses key behavioral traits: the operation is asynchronous ('202 + Location poll'), it 'saves process_mortgage_document.json' as a side effect, and empty optional fields are omitted. It also warns about API parameter casing ('isAsync' vs 'IsAsync'). It does not cover failure modes or the exact JSON schema of saved output, but this is above-average transparency.

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 but each sentence provides value, starting with the core purpose. It is well-structured, moving from API endpoint to request body to input specifics and finally async behavior. The note about 'camelCase isAsync (true), not IsAsync' is a minor distraction but adds implementation clarity. No redundant phrases.

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 no annotations, no output schema, and five parameters, the description covers the purpose, API details, input constraints, async workflow, and output file. The main gap is output_dir, which is not explained, but the rest is sufficiently complete to allow correct invocation. The description compensates well for missing structured metadata.

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?

With 0% schema description coverage, the description adds meaning to several parameters: pdf_file_path ('local .pdf only, must be a PDF file'), doc_name ('optional (basename)'), document_type ('hint, e.g. loan—omitted when empty'), and custom_field_keys ('PascalCase only when non-empty'). However, output_dir is never mentioned in the description and remains undocumented, leaving a gap for that parameter.

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 explicitly states the tool 'extract[s] structured data via PDF4me POST /api/v2/ProcessMortgageDocument', naming the specific domain (mortgage documents) and a clear action. This distinguishes it from sibling process_* tools like process_bank_cheque or process_invoice by focusing on a unique document type. The verb 'extract' and resource 'structured data' make the purpose unambiguous.

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 input constraints: 'pdf_file_path (local .pdf only, must be a PDF file)' and notes doc_name is optional basename. However, it does not explicitly compare to alternative tools or state when not to use this tool. With many process_* siblings, naming alternatives would have strengthened this dimension, but the domain-specific context implies usage for mortgage documents.

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