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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial non-obvious behavior on top: operation while the tab is hidden or closed, the current-vs-earlier distinction for problems an edit has left behind, and the fact that other tool results may carry their own `problems` list. It also flags the reporting boundary of an empty result.

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 key framing is front-loaded in the first clause, and the long failure enumeration earns its space by showing scope. The final sentences about `current`/`earlier` and cross-tool `problems` lists are terser than the rest and read as compressed notes, slightly reducing readability without being wasteful.

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?

With no output schema, the description carries the burden of explaining return shape and does so at a high level — a problems list with `current` and `earlier` buckets, plus warnings. The precise structure of those buckets is left oblique, but for a diagnostic read tool the essentials an agent needs to act are present.

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%, so `id`, `token`, and `includeWarnings` are already fully documented, and the description adds nothing parameter-specific beyond what is in the schema. Baseline 3 applies; the `current`/`earlier` discussion concerns result fields rather than inputs.

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 and resource ('Lists what went wrong in the user's tab') and immediately enumerates the concrete failure classes it covers — render failures with engine messages, stalled previews, load/decode failures, missing footage, failed exports, killed pages, warnings. It is clearly distinguishable from check_playback and from the inspection tools, so an agent can pick it without opening the 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 real operating context ('works while the tab is hidden or closed') and names the alternative with its condition: an empty list only covers what the tab has played, while check_playback does a full pass. It does not spell out the flip side — when this tool should be preferred over check_playback for a first look — leaving that one inference to the agent.

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