Prepare Attachment

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

Annotations already mark this read-only/non-destructive, and the description adds the key behavior: PDFs are rasterised per page and image paths are returned, while images are passed through unchanged. It does not mention side effects like temporary file creation, but the annotation safety profile lowers that burden.

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 command and the critical ALWAYS warning are front-loaded, and the combine guidance is compressed into conditional sentences. The phrase 'which is the right shape when the pages are one document' slightly restates the earlier 'joins the pages of ONE document', but the overall length is appropriate and every sentence earns its place.

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 an output schema present, the description doesn't need to document return values in depth, and it covers the main decision an agent faces (PDF vs image, one document vs several). Minor omissions like dpi semantics and temporary-file behavior do not prevent correct selection or invocation.

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 schema has 0% description coverage, so the description must carry parameter meaning. It explains combine's allowed values and the one-document vs multi-document decision rule, but dpi is left entirely to inference and file_path is only implied as 'file'. This is a real but not fatal 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?

The description opens with a concrete transformation ('Turn a file into something Manager will accept as evidence') and names the exact failure it prevents (Image field rejects PDFs). It clearly identifies this as a pre-attachment rasterisation step, which separates it from the sibling manager_* CRUD tools.

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?

It gives an explicit ALWAYS rule for PDFs before attaching, says images pass through untouched, and provides conditional guidance for combine='vertical'/'horizontal' vs 'none' based on whether pages form one document. It also adds an exclusion: never merge two different proofs. This is explicit 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.