convert_file

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

With no annotations, the description carries the full burden, and it does disclose two genuinely useful traits: the cost model (3 credits per page or sheet) and the side effect that a local path is read on the machine and uploaded. It omits error behavior, whether both inputs can be supplied at once, and the size limits except for the path param.

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 sentences, front-loaded with the core purpose and formats, then input options, then cost. Every clause carries information and there is 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?

For a no-annotation, no-output-schema tool with 2 optional params, the description covers purpose, input modes, output form, and cost. It leaves open the mutual exclusivity of url/path and failure handling, but nothing critical to a correct call is missing.

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 only 50%, so the description must compensate, and it does: the 'public file URL' qualifier constrains url beyond a bare URI type, and 'read on this machine and uploaded' clarifies the path parameter's behavior and implicit upload side effect.

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 (convert) and enumerates the exact input resource types (PDF, XLSX/XLS/CSV, DOCX) and the output shape (text and tables). It does not explicitly differentiate from the sibling read_url, which also retrieves content, so an agent must infer the split from the format list alone.

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 explains how to supply input (public URL or local path, uploaded from this machine), which implies usage, but never states when to choose this over read_url or what conditions favor one input mode. No exclusions or prerequisites are given.

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