vision.observe

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

No annotations are provided, so the description bears full responsibility. It mentions 'durable' and 'no browser' but lacks details on side effects, required permissions, whether it writes to persistent storage, or if it is destructive. The description minimally discloses behavior.

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 description is a single, well-structured sentence that immediately states the core action and key constraint. No extraneous words; every part earns its place.

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?

Despite having an output schema, the description does not explain what constitutes 'OBSERVED evidence', the expected input types (e.g., file path, camera), or how parameters like 'target' or 'source_id' are used. Given the tool's complexity (6 parameters) and lack of schema descriptions, the description is insufficient for complete understanding.

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 input schema has 0% description coverage (no descriptions on any parameter). The tool description adds no explanation of the 6 parameters, their roles, or how they relate to the tool's function. This forces the agent to guess parameter semantics.

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?

The description clearly states the verb 'capture', the resource 'local visual target', and the resulting 'durable OBSERVED evidence'. It also explicitly notes 'no browser', distinguishing it from browser-based tools. This provides specific and unambiguous purpose.

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?

The description implies this tool is for capturing visual evidence locally without a browser, but it provides no explicit guidance on when to use this tool versus alternatives like vision.capabilities, vision.query, or vision.verify. There are no exclusions or comparisons.

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