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

Annotations already declare readOnly, idempotent, non-destructive, closed-world; the description adds that the call is pure local rendering ("no fetches or external writes") and that output is inline file bytes plus a SHA256. That confirms the side-effect profile rather than restating it. Minor gap: no note on size or cost behavior for large inputs.

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, zero filler. The core purpose is front-loaded, with constraints and the return contract following in priority order.

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, zero-side-effect converter with annotations and an output schema, the description covers purpose, input restrictions, side-effect boundaries, and return shape. Nothing an agent needs in order to call it correctly 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 0%, so the description carries the burden and does: the single `markdown` argument is Markdown text, limited to a headings/paragraphs/lists subset and restricted to Windows-1252 characters. It doesn't mention the 131072-character cap, but that is visible via maxLength in 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?

Clear specific verb and transformation: "Render caller-supplied text Markdown to a real downloadable PDF," followed by the supported element subset and encoding limit. The resource is unambiguous and clearly distinct from the sibling converters (csv_to_xlsx, zip_text_files, etc.), though no sibling is named explicitly.

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?

The exclusions act as strong negative guidance: "No images, HTML, fetches or external writes" and "Windows-1252 text only" tell an agent exactly when this tool will not serve. It stops short of naming an alternative tool for unsupported inputs, so no explicit routing beyond the self-exclusion.

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