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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, but they do not convey that this returns a temporary credential rather than performing the upload. The description supplies that, plus the non-destructive two-phase nature of the operation. It stops short of stating how long the signed URL remains valid or what happens if the PUT fails or the content_type mismatches.

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, front-loaded with the action and immediately followed by the critical clarification. Each sentence carries a distinct fact (what is created, what is not done, how to complete the upload, how the result is consumed); nothing is redundant.

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?

Even though an output schema exists, the description names the two key returned fields and explains how each is used, which is exactly what an agent needs to chain the call into a post or draft. For a two-parameter tool with full schema coverage, nothing essential to 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% and the enum of accepted MIME types is fully enumerated in the schema, so the description adds no parameter-level meaning. It mentions the returned signedUrl and media_id fields instead, which is useful but belongs to output semantics, not inputs. Baseline 3 applies when the schema already does this work.

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?

"Creates a signed upload URL and media_id" is a specific verb plus concrete dual artifacts, and the follow-up sentence "creating the URL alone does not upload anything" prevents the most likely misreading of the name. An agent can distinguish this from create_post/create_draft because the description frames it as the media prerequisite, not the publishing step.

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?

It lays out the exact downstream workflow: PUT the raw bytes to data.upload.signedUrl, then use media_id as media[].url in posts and drafts. That effectively routes the agent to the right siblings at the right time, but it never states when not to call it (e.g., an existing media_id can be reused via get_media) or any preconditions such as account/permission requirements.

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