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

Annotations already declare readOnly, idempotent, non-destructive, so safety is covered; the description adds genuinely new behavior: base64 encoding and a ~600 KB cap, plus a routing hint to a cheaper alternative. It stops short of saying what happens at the cap (truncated vs. error), which is the one thing an agent most needs to know.

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, zero filler; the size cap is front-loaded and the alternative is offered immediately after. Every clause earns its place.

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?

For a simple two-parameter read tool with full annotations and no output schema, the description covers return content (base64 bytes) and limits. The residual gap is the ambiguous cap semantics and the undocumented id parameter.

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 only 50%: token is documented, id is bare. The description never mentions either parameter, so it adds no meaning about what id refers to (file id? message id?) or how the session token is scoped, leaving half the parameters undocumented everywhere.

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?

Specific verb+resource: "Returns the raw bytes of one file, base64, capped at about 600 KB." It also implicitly separates itself from text-oriented readers by stating it returns raw bytes. An agent can distinguish it from inspect_media and list_media without opening schemas.

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 the alternative (inspect_media) and the exact conditions that select it: "For larger files and for video." That is a when-to-use/when-not-to-use pair with a concrete tradeoff (size).

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