get_attachment

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

Well beyond the readOnlyHint/destructiveHint annotations: it discloses the exact response shape per MIME type, size caps for each tier (3.75MB images, 5MB text), the truncation flag and metadata-only fallback, and a prompt-injection caveat about third-party file contents. That is precisely the behavioral context an agent needs before calling.

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 action, and every sentence carries information. The type-tier sentence is a dense run-on that would read better as a short list, but nothing is padded.

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?

There is no output schema, so the description must define return values — and it does so exhaustively across all three response shapes, plus the truncation edge case. An agent can predict exactly what it will receive before calling.

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 maxSizeBytes default, cap, and truncation semantics are already spelled out in the schema, so the description largely restates them. It adds cross-parameter meaning (which content types are subject to which cap), but not enough to exceed the baseline.

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?

Opens with a specific verb+resource ('Download an attachment by id') and immediately characterizes what comes back. No sibling returns attachment bytes, so it is unambiguous against upload_attachment and the get_* entity tools.

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?

Usage is implied (you need an attachment id and want its contents), and the size/type tiers help an agent anticipate cost. But it never says where an id comes from, what to do when truncated, or when an alternative (e.g. fetch the parent entry) is preferable.

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