Vision Chat

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

Annotations already declare readOnlyHint=false, openWorldHint=true, and non-idempotency, so the safety profile is partly covered. The description adds genuine context the annotations cannot: that dry plans make zero provider calls, that a live submission needs explicit workflow authorization plus a configured model/account, and that model interpretation is separate from source byte lineage. It stops short of describing cost, latency, or failure behavior on live calls.

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 sentences with the purpose front-loaded and no filler; the dry-versus-live distinction follows immediately. The phrasing is somewhat abstract ('bounded source video samples', 'source byte lineage'), costing a little readability but not wasting space.

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. For a single nested request parameter at full schema coverage, the description supplies the key operational context (dry default, authorization gate, provider dependency) that an agent needs before invoking. It could say more about which sources are valid or how the live path behaves on failure.

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 the nested request object, limits, sources, crop, and resize semantics are already documented in the schema. The description adds the dry/live authorization framing but no field-level syntax or defaults beyond what the schema provides, so the baseline 3 is appropriate.

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 opens with a specific verb triad (analyze, identify, compare) and a precise resource ('exact images and bounded source video samples'), which is more than a restatement of the name. It does not, however, explicitly distinguish itself from close siblings like vision_ocr, vision_grounding, or video_analyze, leaving the agent to infer the boundary.

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 implies usage context by contrasting 'dry plans' (local, zero provider calls) with a 'live request' that requires explicit authorization and a configured model/account, which maps to the dry_run and authorize_submission flags. It never states when to prefer this tool over vision_ocr, vision_grounding, or video_analyze, so the routing decision is left implicit.

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