Vision (read)

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

Adds real behavioral context beyond the annotations: 'playhead is restored' discloses a transient side effect, 'macOS, needs Screen Recording permission' discloses an OS and auth prerequisite, and 'Resolve not needed' discloses that source_frames works outside the app. These are exactly the operational facts annotations cannot carry.

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-loaded purpose sentence, then a single compact action table with a legend for the `*` convention. Every bullet adds distinct information; no filler or repetition of the annotation flags.

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, polymorphic op-dispatch tool this is complete: purpose, per-action params and requirements, platform/permission caveats, and side-effect notes are all present, and an output schema exists so return values need not be described.

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?

The schema only exposes an open `op` object, so the description carries the entire parameter burden — it lists every action's parameters with `*` marking required ones (path*, seconds* for source_frames). This goes well beyond the 100% schema coverage baseline by documenting per-action param semantics the schema cannot express.

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 ('Read vision state, no side effects') and then enumerates all five actions with concrete outputs (tiled JPEG, frame capture, ffprobe summary, window screenshot, ffmpeg extraction). An agent can distinguish this from timeline_read/media_read purely from the action list.

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?

'use it to find ids and check results' gives the primary use case, and each action bullet implies when it applies (e.g. 'Resolve not needed' for source_frames, 'at timecodes / markers' for contact_sheet). It never explicitly excludes alternatives or points to describe_action for parameter discovery beyond the one mention.

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