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

Adds substantial behavior beyond the annotations: waitSeconds does not start work or consume credits, the canWait re-call pattern, the full list of terminal states (disabled, upgrade_required, quota_exceeded, unsupported, failed), how reason explains stoppage, and that ready analysis jobs carry their answer in result. This is exactly the state-machine context annotations cannot convey.

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?

Dense but front-loaded and purposeful — purpose, mediaId meaning, and jobId semantics come first, states and status guidance after. Nearly every sentence is actionable, though the single long paragraph runs on and could be split for scannability.

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?

An output schema exists, so return values need not be spelled out, yet the description still explains result and note fields helpfully. Combined with the terminal-state list and alternative routing, an agent has what it needs; the waitSeconds range mismatch with the schema is the one loose end.

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 coverage is only 33% (only mediaId is documented in the schema), so the description must compensate, and it does: it explains jobId as null-vs-job-uuid and details waitSeconds' wait semantics and credit-free behavior. Minor imprecision: it says waitSeconds 1–25 while the schema permits 0–25.

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?

Opens with a specific verb+resource: 'Read Video Intelligence progress for a video.' It clearly distinguishes itself from the producer siblings index_video and analyze_video, positioning itself as the polling/status reader for their jobs rather than a job starter.

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?

Explicit routing: jobId null reads the whole index, otherwise pass the jobId returned by index_video or analyze_video. It states when to wait (waitSeconds), when not to (terminal states should not be looped or silently restarted), and names the follow-up call for not_indexed (index_video).

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