Ask the LLM about a TOP (multimodal)

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

The description adds meaningful behavioral context beyond the readOnlyHint annotation: it explains egress requirements for remote backends, states that returns are redacted, and notes `calibration: not_checked`. It also discloses implementation via ctx.llm.complete(). No contradiction with annotations.

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 concise sentences with no fluff. The main purpose is front-loaded, followed by key constraints and a sibling differentiation.

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?

The description covers the core operation and key edge-case constraints (egress, calibration). However, since there is no output schema, it would be helpful to explicitly state that the response contains the LLM's answer; it is implied but not stated. Overall, it is fairly complete for the tool's complexity.

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?

All parameters are already described in the schema (100% coverage), so baseline is 3. The description adds value by clarifying when `allow_remote_image_egress` is needed and by explaining the role of `source_top` in the capture process, enhancing the schema descriptions.

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 tool captures a TOP as a preview image and asks a multimodal LLM a question about it. It distinguishes itself from sibling `caption_top` by noting the different behavior (deterministic vs open-ended).

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?

Provides context on when to use the tool by contrasting with `caption_top` (deterministic vs open-ended) and states it is not the calibrated visual-mutation authority. It also gives configuration guidance for when `allow_remote_image_egress` is required, but does not explicitly enumerate all alternative tools or exclusion cases.

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