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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=true, openWorldHint=true), and the description adds substantial context on top: the operation is asynchronous, it does not confirm a platform post, repeated calls with the same key and recognized settings replay the original accepted snapshot even after completion, and changed recognized settings yield a 409. That is exactly the kind of side-effect and retry behavior an agent cannot infer from the annotations.

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 purpose is front-loaded in the first sentence, followed by the async caveat and then the idempotency rules in a logical order. It is dense but nearly every sentence carries distinct information; the only mild redundancy is re-stating the 1–128 printable ASCII key constraint that the schema already spells out.

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 nested, six-parameter mutation with no output schema, the description covers the important behavioral ground: async enqueue, no confirmation of the platform post, idempotency recovery, and conflict behavior. It stops short of saying what the accepted job snapshot contains (e.g. a job id usable with getVideoStatus) or what permissions/account connections are required.

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 83%, so the parameters are largely self-documenting and the baseline would be 3. The description adds meaning beyond the schema by defining what counts as the "same" request for idempotency comparison (JSON formatting, property order, and unrecognized fields are ignored; recognized setting changes produce 409), which directly governs how a caller should construct this call.

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 opening line names a specific verb and resource ("Queue a video publish") and the follow-up clarifies the semantics: an atomic durable enqueue that returns an accepted job snapshot rather than a completed platform post. That distinguishes it from a synchronous publish, though it never explicitly names siblings like publishPost, publishStory, retryVideoPublish, or scheduleVideo.

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 gives implied usage context (this is a queue/enqueue, not a confirmation) and a concrete recovery instruction for using the Idempotency-Key when the response is lost. However, it never states when an agent should choose this over publishPost, scheduleVideo, or retryVideoPublish, so the routing decision is left to inference from the name.

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