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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds meaningful behavior beyond that: the 1-5 document cap, per-document return fields (markdown, format, characters, approxTokens, truncated), and the OCR limitation.

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?

Three dense sentences, front-loaded with purpose, then input modes, then return shape and limitations. Nothing is wasted, though the format enumeration makes it slightly heavy.

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?

With no output schema and low schema coverage, the description carries the burden well: it names the return fields, the input modes, the batch cap and the OCR exclusion. Only maxChars/truncation control is left implicit.

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 33%, but the description compensates by explaining the urls vs files:[{name, base64}] shapes and the batch limit. It does not mention maxChars at all, so roughly a third of the parameter surface remains undocumented outside 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 (convert) and resource (documents) and enumerates the exact accepted input formats plus the batch limit of 1-5. An agent immediately knows this is document-to-Markdown conversion, not a format lookup like the sibling supported_formats.

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?

Gives positive context ('for reading or RAG') and an explicit exclusion ('Not for images or scanned PDFs (no OCR)'). It also explains the two input modes (public URLs vs base64 files), though it does not explicitly route to or contrast with the sibling tool.

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