Get file

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

Annotations already declare readOnlyHint, idempotentHint and closed-world behavior, so 'Read-only; changes nothing' largely restates what the agent already knows. The description does add real value by disclosing the response payload (base64 bytes plus filename, content type and size) and the remote-vs-local mode split, but it says nothing about size limits, truncation, or failure modes beyond what the schema states.

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?

Three sentences, front-loaded with what the tool returns before explaining how to address the file. Mostly earns its place, though the 'Read-only; changes nothing' clause is redundant against the annotations and could be dropped.

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 present, the description takes on the burden of describing the return value and does so fully: base64 content plus filename, content type and size. Combined with the mode distinction for identifiers and the pointer to the remote file list, an agent has everything needed to call it correctly.

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?

The description adds a genuine addressing rule beyond the schema: filename works in 'either mode' while fileId is 'remote mode only', clarifying that the two identifiers are not interchangeable across backends. Since schema coverage is already 100%, this is useful corroboration rather than new field documentation.

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 a file attached to a task') and immediately names the return shape ('base64 with its filename, content type and size'). It is clearly separable from the sibling attach_file, which writes rather than reads an attachment.

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 concrete when-to-use condition: 'Use it to read back an attachment the file list only names — the remote list carries no bytes.' That tells the agent why it cannot substitute a listing call. It does not name an explicit alternative tool or a when-not-to-use case, so it stops short of a 5.

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