get_attachment

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

The description discloses detailed behavioral traits beyond the readOnlyHint and destructiveHint annotations: image/* returns native image content, text/* and application/json return decoded text, other binary types return metadata + base64, and files exceeding maxSizeBytes return truncated metadata only. This is exactly the kind of response behavior an agent needs to handle results correctly.

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, front-loaded with the core action and resource, followed by a compact breakdown of return formats for different MIME families. No filler or redundancy; the brief mention of maxSizeBytes default in prose contextualizes the truncation flag without bloating the description.

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 fully carries the burden of explaining return values, and it does so across all relevant cases: images, text/JSON, binary types, and oversize truncation. Parameter semantics are fully covered by the schema, so nothing an agent needs to call the tool correctly is missing.

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 100%, and the schema already documents both parameters, including maxSizeBytes' default (5242880), maximum (26214400), and truncation behavior. The description repeats the default but adds no new parameter semantics beyond what the schema provides. 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: 'Download an attachment by id.' The type-specific return details reinforce that this is a retrieval tool, not a mutation. It clearly distinguishes itself from the upload_attachment sibling by its download focus.

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?

The description makes the tool's purpose unambiguous: retrieve attachment content by id. It doesn't explicitly name alternatives or when-not-to-use conditions, but the only related sibling (upload_attachment) is the inverse operation, so there is no genuine alternative for downloading. This provides clear context without needing explicit exclusions.

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