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

Annotations cover the safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), and the description adds genuine beyond-annotation context: the URL is one-time, the PUT must happen 'in this same runtime', and returned headers must be sent exactly. This is valuable operational disclosure, though it doesn't discuss auth/permissions or failure modes for the upload PUT itself.

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?

Well front-loaded (core purpose stated first) and structured with a numbered three-step flow plus a fallback clause. Each sentence carries operational value, though the description is on the longer side for a two-parameter tool and the final fallback sentence could be tightened.

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 multi-step tool with an output schema already defining return fields, the description supplies everything else an agent needs: the ordered flow, the same-runtime constraint, exact-header requirement, and a graceful degradation path. Nothing critical for correct invocation is missing.

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 both parameters are already documented, including examples of content_type MIME values. The description clarifies why content_type is passed (the file's MIME type) and how the returned media_id is consumed, but adds no syntax or constraints beyond the schema, so baseline 3 applies.

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+resource ('Get a one-time presigned S3 URL to upload an image, video, GIF, or PDF') and ties it to a concrete downstream use. It effectively distinguishes itself from siblings like attach_media_from_url and upload_media by clarifying that the agent holds the bytes locally and receives a URL rather than uploading directly.

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 explicit when-to-use ('Use when the agent holds the bytes locally') and an explicit when-not/alternative ('If this runtime cannot PUT raw bytes to a URL, skip it: create a text-only draft and tell the user to attach the media in the Taplio composer'). The alternative path is named concretely, leaving nothing to inference.

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