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

Annotations already cover safety (readOnly, idempotent, non-destructive), yet the description still adds substantive behavior: text returns decoded text, images return viewable bytes, small binaries return base64, files over 8 MB return metadata only, and read access to the issue is required. This is exactly the kind of return-shape and limit disclosure the annotations cannot convey.

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?

Front-loaded with the core action, then layers return-format behavior and limits in a compact sequence. Every clause carries information, though the return-format list is dense enough that tighter phrasing would help.

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 no output schema, the description compensates fully by explaining the differing return shapes (decoded text, viewable image, base64, metadata-only over 8 MB) plus the permission requirement. An agent has everything needed to call and interpret it.

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% and both parameters are documented in the schema itself, so the schema does the heavy lifting. The description only reiterates the provenance of attachmentId ('get the id from list_issue_attachments or get_issue'), which is marginal added meaning.

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 ('Read the content'), resource ('one Issue attachment'), and access key ('by id'). It is clearly distinguishable from list_issue_attachments and the parallel read_task_attachment tool.

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?

Explicitly tells the agent where to obtain the id (list_issue_attachments or get_issue) and states the permission precondition ('Caller must be able to read the issue'). It does not, however, distinguish when to use this vs the sibling read_task_attachment, so the exclusion is missing.

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