Vision Ocr

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

Annotations declare readOnlyHint=false, openWorldHint=true and idempotentHint=false, so the agent already knows this is a non-idempotent, open-world model call. The description usefully adds that output is labeled inference rather than ground truth and that no silent fallback happens, but omits the significant operational fact that dry_run defaults to true and authorize_submission must be granted before a real run.

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?

Three short sentences, front-loaded with the core action and followed by the differentiator and the no-fallback caveat. No filler, though 'Model transcription is labeled inference' is phrased awkwardly enough to cost a little clarity.

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 no explanation, and the model-vs-local distinction is covered. What is missing for a non-read-only, open-world tool is the dry-run-default and explicit-submission workflow, which the agent must discover from the schema rather than the description.

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 nested request object is thoroughly documented, including crop, resize, limits and the dry-plan/submission grant. The description adds no parameter-level detail 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+resource ('Infer visible text from exact prepared images or precise source frames') and explicitly distinguishes itself from the sibling image_ocr, which uses local Tesseract/Vision. An agent can separate the two model-vs-local paths 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?

It names the alternative (image_ocr) and asserts 'No automatic fallback occurs', which tells the agent the choice is explicit and must be made deliberately. However it never states when a model-based transcription is preferable to the local observation path, so the routing decision is only half-specified.

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