문서로 내보내기

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

Annotations only declare the generic non-read-only, non-destructive, closed-world profile; the description adds real behavioral detail beyond them, notably that pdf returns a first-page preview and that failures surface errors with TeX problems pinpointed on the `!` line. It stops short of saying what docx/pptx return or where files are written.

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?

The core action is front-loaded in the first clause, followed by a compact example and layout notes. It is dense and slightly telegraphic ("On failure: follow errors") but nearly every sentence carries information an agent needs.

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 five parameters, a 20% schema coverage, and no output schema, the description does the heavy lifting on format/layout semantics and error handling. It leaves minor holes: no explanation of the `name` parameter and no statement of the return payload for docx/pptx.

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 description coverage is only 20%, so the description must compensate, and it does: it explains what markdown may contain, the meaning of each format choice, and the structural contract implied by each layout value. The `name` parameter and the `title` parameter are only touched indirectly (title appears in the example, name is never explained), leaving a small gap.

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 and resource (save markdown as pdf/docx/pptx) and enumerates the supported content types (math, images, tables). It also implicitly separates itself from the render_*/plot_* siblings by naming them as the source of image paths rather than as alternatives for this task.

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 conditional guidance for choosing a layout: cheatsheet means one A4 page in pdf, exam expects a problems section followed by an answers heading, flashcards means a two-column table in pdf. It does not state when to prefer this tool over siblings like read_document or get_template, so tool-selection guidance is absent even though configuration guidance is strong.

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