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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds real behavioral context beyond them: only page 1 is processed, document type is auto-detected, results carry per-field confidence, and there is no payment/cost. It still omits error behavior for bad URLs or unsupported PDFs.

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 core sentence is front-loaded and dense, but 'Free' appears twice and the bracketed '[falcon.sol docs. Free, no payment.]' fragment is noise that repeats the pricing point without adding information.

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 zero required parameters and no output schema, the description should clarify that at least one of url/file_base64 must be supplied and what the response contains. It gives only 'per-field confidence' and never addresses the required-input gap, so an agent could invoke it with no arguments.

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 coverage is 67%, so the baseline is 3. The description usefully explains that the 'type' parameter's values correspond to auto-detected document classes (invoice/receipt/PO/W-9/bank statement), but it does not clarify url vs file_base64, which is the key ambiguity in this schema.

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?

States a specific verb and resource: extract page 1 of a PDF, with auto-detection of five document types plus per-field confidence. The 'page 1'/'preview' scope is clear, but it never names or distinguishes itself from the sibling extract_document, leaving the agent to infer that this is the truncated, free-tier variant.

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?

'Free: ... Free, no payment' signals this is the no-cost preview path, implicitly contrasting with a paid extraction tool, but no explicit alternative is named and there are no when-not conditions. An agent can guess this is the cheap first-look call, but the routing rule to extract_document is never stated.

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