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

Annotations already establish readOnlyHint=true, but the description adds real behavioral context: the 5242880-byte inline cap, which content types are inlined, and the edge case where an attach token has no attaches entry (deleted attachment or copied text). The last sentence is terse but discloses a failure mode the schema does not.

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 dense sentences with the core behavior (what comes back and the size/type limit) front-loaded, followed by the edge case. No filler.

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 correctly spends its budget describing the return shape (image as image, text as text, size cap, non-inline types) and one failure mode. It still leaves unclear what the caller actually receives for a non-inline file, which is the main remaining gap.

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 fid description already explains the 'attach:<fid>' relationship, so the schema carries the parameter burden. The description adds no format or constraint detail for the optional entity object beyond what the schema states.

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 ('Returns a file's content by fid') and immediately scopes it with return-format rules, which separates it in spirit from file_info and file_url. It never names those siblings, so the differentiation is inferable rather than explicit.

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?

Gives a clear when-not condition: larger files, video, archives and other binaries are not returned inline, so an agent knows this tool won't work for those cases. It does not route the agent to an alternative (file_url, file_info) for the non-inline cases.

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