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

The description goes far beyond the minimal annotations by disclosing that this tool only mints a URL rather than uploading a file, that the caller must PUT the file separately, and that failing to do so causes create_post/bulk to reject the media. This is critical behavioral context the agent could not infer from readOnlyHint/destructiveHint alone.

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?

The description is front-loaded with the core purpose and includes essential workflow details. It is longer than necessary because the supported-types list duplicates the schema enum, but every other sentence contributes meaningful guidance.

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?

Given the output schema exists, return values are covered structurally. The description supplies everything else needed: when to use it, how the returned URLs relate to create_post, the required manual upload step, the error consequence, and the preferred sibling alternative.

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 schema already documents files, fileName, and mimeType with 100% coverage, so the baseline is 3. The description adds 'For each file, provide fileName and mimeType' and repeats the supported types, which mirrors the enum rather than adding substantial new semantics about the parameters themselves.

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 description states a specific verb and resource: 'Get presigned upload URLs for direct file uploads.' It clearly differentiates this tool from the upload_media sibling by noting that upload_media performs the upload, making the scope of get_upload_urls unmistakable.

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 explicitly recommends 'Prefer the upload_media tool, which performs the upload for you,' giving a clear alternative. It also explains the sequential requirement: PUT to uploadUrl and confirm a 2xx response before using publicUrl, with a concrete failure mode ('Media file(s) not found in storage').

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