download_attachment

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

The description adds meaningful behavioral context beyond the annotations by explaining that downloads go to a process-scoped temporary cache and that the cache is removed on server shutdown. This gives the agent important expectations about the returned local_path's lifetime and scope.

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?

Two sentences, both necessary. The main action and return value are front-loaded, and the cache lifetime detail is placed second, making the description both concise and logically structured.

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 single-parameter tool with a true output schema and read-only/idempotent annotations, the description covers the essential behavioral details: download action, cache scoping, and lifetime. It is slightly incomplete only in that it doesn't mention typical downstream usage of local_path or how it relates to get_attachments.

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 0%, so the description carries the burden of explaining the parameter. It only says 'by id', which essentially restates the schema's 'attachment_id'. It does not clarify where to obtain the id, what format it takes, or distinguish it from other identifiers.

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 states a specific action (download one attachment by id) and a concrete outcome (returns local_path), and clearly distinguishes itself from sibling tools like get_attachments by focusing on a single attachment and returning a cached file path rather than listing or retrieving content.

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?

No guidance is given about when to use this tool versus alternatives such as get_attachments or get_issue. The description implies it should be used when an attachment_id is already known, but it does not explicitly state prerequisites, exclusions, or alternatives.

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