docshelf_add_document

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

Annotations indicate idempotentHint=true but no destructiveness. The description adds crucial behavioral traits: PDF conversion details, auto-splitting logic, INDEX.md regeneration, and the caller's responsibility for committing. No contradiction with annotations.

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 description is front-loaded with the main purpose followed by bullet points. Every sentence adds value without redundancy, making it efficient and easy to parse.

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?

Given the complexity (multiple parameters, conversion, splitting, index update) and the presence of an output schema, the description covers most important behaviors. Minor gap: no mention of error handling or prerequisites (e.g., file existence), but overall sufficient.

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 input schema already describes each parameter well, but the description adds meaningful beyond-schema context, such as default conversion method, the 'quality' option, and split behavior. Schema descriptions exist for all parameters, but the description enhances understanding.

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?

The description clearly states the action ('Add a PDF or Markdown file to the shelf') and the outcome ('refresh INDEX.md'). It distinguishes from sibling tools by specifying the file types and the shelf context.

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?

While not explicitly stating when to use alternatives, the description implies usage for adding new documents. The sibling tool names (e.g., convert_pdf, search) are sufficiently different, so the context provides implicit guidance.

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