Ask the LLM about a TOP (multimodal)

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

The description adds substantial behavioral context beyond the readOnlyHint and destructiveHint annotations. It discloses egress requirements (loopback vs. remote), return fields ('redacted egress locality/transport' and 'calibration: not_checked'), role limitations ('NOT the calibrated visual-mutation authority'), and implementation details (uses ctx.llm.complete() with an image part). 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?

Four sentences, each earning its place: purpose, egress conditions, return/limitations, implementation, and sibling differentiation. The description is front-loaded with the primary action and avoids fluff or redundancy.

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 tool's purpose, egress constraints, return summary, and differentiates it from a sibling. Without an output schema, it does not fully specify the complete return structure, but the primary output (the LLM's answer) is implied. It is adequate given the tool's complexity and annotation coverage.

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?

With 100% schema coverage, the baseline is 3. The description enriches parameter semantics by explaining when `allow_remote_image_egress` is required (remote, client-managed, or unknown backends) and clarifies that `source_top` is captured as a preview image. This adds meaning beyond the schema's generic wording.

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+resource: 'Capture a TOP as a preview image and ask the configured multimodal LLM a question about it.' This clearly states what the tool does and distinguishes it from the sibling `caption_top` by explicitly noting it is 'Different from `caption_top`, which is deterministic-by-default.'

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 when to use the tool by contrasting with `caption_top` and by stating it is 'NOT the calibrated visual-mutation authority,' which excludes calibration/mutation use. However, it does not explicitly say 'use this when you need an open-ended or non-deterministic answer' or provide explicit usage scenarios beyond the core action.

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