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

With no annotations, the description carries the full burden and discloses important behavior: max size, conversion backend, return shape, URL safety rules by reference, failure billing exemption, and per-call cost via x402. These details go well beyond the schema.

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?

Five short, information-dense sentences with the primary action front-loaded. Each sentence contributes distinct, actionable detail (size, return, safety, billing, cost) without 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 one-parameter read tool with no output schema, the description is complete: it covers the input constraint, return fields, cost model, and failure billing. The reference to read_url's safety rules is acceptable given the sibling tool is available.

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 single 'url' parameter is fully documented in the schema (100% coverage), so baseline is 3. The description adds the 10 MB limit and reiterates that the target must be public and a PDF, providing extra constraint meaning beyond the 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 (Fetch), resource (public PDF), transformation (convert to Markdown), and return fields. It is clearly distinguishable from sibling read_url because it targets PDFs, not generic URLs.

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?

Provides clear context and constraints for use: public PDF, max 10 MB, same safety rules as read_url, and cost. However it does not explicitly name read_url or read_url_safe as alternatives for non-PDF or unsafe URLs, so it lacks full when/when-not guidance.

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