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

With no annotations provided, the description must disclose behaviors on its own. It accurately states the tool creates a job, polls until terminal state or timeout, and returns a signed URL only on completion. It also mentions the timeout behavior and the return payload. It does not explicitly state what happens on failure (e.g., does it throw an error or return the failed job?), but the phrasing 'returns the final job' covers that. The description adequately discloses the main operational traits.

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?

Two sentences with no filler. The first sentence packs the full behavior (create, poll, terminal state, return value) and the second delivers the usage guidance. All information is front-loaded and every word earns its place.

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 six parameters including nested objects, no output schema, and no annotations, the description provides a clear mental model of the operation: create, poll, return. It explains the return value (final job + signed URL if completed) and the timeout behavior. Missing details like error handling or cost/performance implications are minor for a convenience tool. The description is sufficient for correct invocation.

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% with detailed per-parameter descriptions (e.g., inputs max/min, preset vs. options precedence, timeout defaults). The tool description adds minimal parameter-specific detail beyond the schema; it only contextualizes timeout and polling implicitly through the overall workflow. Baseline 3 applies since the schema already carries the semantic load.

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 clearly identifies the tool as a one-shot convenience wrapper that creates a transcode job, polls to a terminal state, and returns the job plus a signed download URL. It uses a specific verb sequence and names the exact resource, making it distinct from siblings like transcode_video (which likely just submits) and get_transcode (which just reads status).

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 final sentence explicitly states when to use this tool: 'when you want the full transcode in one step without managing polling yourself.' This implies the alternative (manual polling via separate calls) and provides a clear selection criterion. However, it does not name the specific sibling tools (e.g., transcode_video, get_transcode) or state when not to use it beyond the implied case.

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