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

Annotations already declare readOnly/non-destructive, but the description adds substantial context beyond them: the payload is base64 text, it inflates token cost by roughly a third, there is a size ceiling, and the file bytes are transmitted into the conversation. That cost and ceiling disclosure is exactly what an agent needs before calling a read tool that can flood context.

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-loads the verb, resource and return format in the first clause, then layers cost, alternative, and permissions. Each sentence carries information, though the parenthetical about local_files_setup slightly lengthens an already dense block.

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 still covers what comes back (base64 bytes), the practical consequence (context cost, size ceiling), an escape hatch for large files, and the authorization model. Nothing an agent needs to call this safely is missing, aside from a precise ceiling value.

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 the schema already documents both parameters, including 'as listed by get_issue'. The description reinforces the workflow dependency (filename must match what get_issue lists) but adds no syntax or format detail beyond that, so the baseline 3 is appropriate.

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 and resource ('Read one file attached to an issue') and even specifies the return encoding ('its bytes, base64-encoded'), which lets an agent distinguish this from mutation tools like add_attachment. It does not explicitly differentiate from the get_wiki_attachment sibling, so the scope boundary with wiki files is only inferable from the word 'issue'.

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 names an alternative (the pm-files MCP server, reachable via local_files_setup) and the condition that selects it: large files, because bytes in the conversation cost a third more. It also states the access prerequisite ('only permission to see the issue'), so an agent knows when this tool is appropriate and when it is not.

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