serve_media

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

With no annotations supplied, the description carries the full behavioral burden and does so well: it discloses the authentication/authorization model, the signed-URL path, and the special case of orphaned private media. It is silent on response characteristics (binary vs redirect, content type, caching), which keeps it out of the top band.

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?

Four short sentences, no filler, and the critical access rules are stated before the endpoint notation. The opening 'Serve Media' duplicate of the tool name is wasted space, and the endpoint string would be better placed at the top than the bottom.

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 read-only media-serving call with full schema coverage and no output schema, the description covers the one thing an agent genuinely needs to know before calling: whether it will be authorized. Only minor omissions (response form, redirect behavior) remain.

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%, so uuid, exp, sig and download are already fully documented in the schema, and the description adds nothing further about them. Baseline 3 applies, though the auth paragraph indirectly motivates the exp/sig pair.

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?

The 'GET /uploads/{uuid}' line plus the auth paragraph make clear this fetches/returns media for a given UUID, which is concrete enough for an agent to select it. The leading 'Serve Media' heading is essentially a restatement of the name, and no sibling (e.g. media_upload, download_conversation_transcript) is mentioned for contrast, so it stops short of a 5.

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 does spell out the access conditions under which the call succeeds or fails (public media unauthenticated, private media needing record access or a signed URL, unattached private media restricted to the uploader), which is genuinely useful when-to-use context. However, it gives no explicit routing guidance against alternatives such as media_upload or the transcript download tool.

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