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

With no annotations, the description carries the full behavioral burden. It does disclose a genuinely useful trait — the cost of 3 credits ($0.003) per page/sheet — but omits authorization needs, whether processing is synchronous, and error behavior for malformed or unsupported files.

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?

Two compact sentences, front-loaded with the capability and followed immediately by the cost. Every clause earns its place with no filler.

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 zero annotation coverage, 0% schema descriptions, and no output schema, the description covers formats, input channels, and cost but leaves key gaps: the url/base64 exclusivity rule, the role of filename, and any return-shape or pagination detail. Solid but not sufficient for a tool with this much structured-field void.

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 0%, so the description must compensate. It clarifies that input can come 'by URL or base64', which maps to two of the three parameters, but leaves filename entirely unexplained and never states whether url and base64 are mutually exclusive or which is required (required count is 0, adding ambiguity).

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 names a specific verb (convert) and enumerates both the accepted inputs (PDF, XLSX/CSV, DOCX via URL or base64) and the outputs (text and tables), so an agent knows exactly what the tool produces. It does not, however, explicitly distinguish itself from the sibling read_url.

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?

Usage is implied by the input format list — you call it when you have a PDF/XLSX/CSV/DOCX to extract content from — but there is no explicit statement of when to prefer this over read_url, nor any prerequisites or exclusions. Adequate but with a clear routing gap.

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