Get Attachment

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

Annotations already mark it read-only and non-destructive; the description adds substantial behavior beyond that: media type classification, when bytes are not downloaded, when rendering is refused, and preview behavior. No contradictions 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?

Rich content earns its place: every sentence adds context or constraint. Slightly long, but each clause carries meaning about when/how to use or when not to use the tool; the key usage context is front-loaded after the first sentence.

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 4-param read-only fetch tool with no output schema, it covers what the model sees, when bytes are not downloaded, which variation to request, where params come from, and the refusal case. An agent can invoke correctly without guessing.

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 100%, so baseline is 3. The description adds real value by explaining where each parameter comes from (signed_id/filename from fizzy_get_card/comments with include_attachments=true), that variation should be omitted appropriately, and that URL/path construction won't work. This is more than the schema alone provides.

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 clear verb ('Fetch') and resource ('a file already attached to a card or comment'), then differentiates from siblings by explaining what comes back. It explicitly distinguishes itself from upload (fizzy_upload_file) and the card/comment list tools that expose attachment metadata.

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?

Goes far beyond a simple trigger: it tells the agent when to use it (any card/comment referencing a screenshot/mockup/diagram/error image where the answer depends on the image), what to prefer (preview_variation), and what not to do (do not build args from a URL by hand). This is exemplary routing guidance.

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