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

Annotations only declare the basic safety quadrant; the description adds substantial behavioral context beyond them: quota pre-charging to defeat a TOCTOU race, automatic refund conditions (no PUT in 10 min, undersized upload, magic-byte failure), the 50MB hard cap, and that the PUT handler creates the Asset doc and validates magic bytes. This is exactly the kind of non-obvious behavior an agent needs.

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?

Front-loads the recommendation and the two-step workflow before the caveats, and every sentence carries operational content. It is long, but the length is justified by genuine complexity; there is minor redundancy in the repeated warnings about not retrying, keeping it below a 5.

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?

Covers the full call lifecycle — request, out-of-band PUT, inline asset-URL return usable in create_post_draft/update_post_draft — plus failure modes, fallback, and quota accounting. An output schema exists, yet the description still tells the agent what the PUT response yields, so nothing needed to invoke correctly 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 0%, so the description must carry the load, and it largely does: it names all three params ({filename, contentType, sizeBytes}), enumerates the allowed content types matching the enum, and states the 50MB cap and size-based quota pre-charge for sizeBytes. Only filename's semantics are left thin, so it falls just short of fully compensating.

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 ('request' an 'asset upload URL' as the 'Recommended upload tool for images and videos') and explicitly distinguishes itself from the sibling `upload_asset` tool. An agent can tell exactly what this does and when it beats the alternative without opening either schema.

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 ('images and videos of any size', 'anything larger than ~8KB'), when-not ('do not call this tool again expecting a different uploadUrl'), and names the alternative (`upload_asset`). It also documents the egress-restricted fallback path with the manual-upload workaround, so nothing is left to inference.

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