A camera still as pixels

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

Annotations cover the safety profile (readOnly, openWorld), so the bar is lower, and the description still adds substantial detail: base64 RGB encoding, 3 bytes per pixel, row-by-row layout, and the credential requirement. It omits error/rate-limit behavior, which keeps it from a 5.

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?

Purpose is front-loaded and every sentence carries information (format, target consumer, alternative, auth). The nested parentheticals (base64, 3 a pixel, two pixels a character cell) make it dense but not 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 the return value, and it does so thoroughly (base64 RGB bytes, 3 per pixel, row-major). Combined with the auth note and sibling routing, an agent has what it needs to call it correctly.

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%, and the schema already documents width, height, entity_id, and instance_id. The description adds the notion of downscaling to at most width x height but no per-parameter semantics beyond that, so the baseline 3 applies.

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: it fetches a camera's current still, decodes it, and shrinks it to at most width x height pixels. It also names the sibling ha_camera_image as the tool for looking at a camera yourself, so an agent can distinguish it without opening either 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?

Explicitly scopes usage to clients that draw pictures in text (terminal dashboard panes, two pixels per cell with half blocks) and routes the user to ha_camera_image for direct viewing. It also states the VomeHome auth prerequisite (Cameras ticked under Sensitive devices).

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