Ask the LLM about a TOP (multimodal)

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

The description discloses behavioral details beyond the annotations, such as using `ctx.llm.complete()` with a MultimodalMessage and returning a specific JSON object. It also clarifies that the tool always routes through the vision model. No contradiction with annotations (readOnlyHint=true, destructiveHint=false).

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 three sentences with no fluff. It front-loads the purpose, outputs, and implementation details, then differentiates from a sibling. Every sentence adds value and is well-structured.

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?

Given no output schema, the description explicitly lists the return fields and mentions error behavior ('friendly error otherwise'). It covers prerequisites and use case differences, making it fairly complete for a tool with moderate complexity (6 params, 2 required).

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 schema already documents all parameters well. The description adds marginal value by mentioning the internal implementation (MultimodalMessage) and the output format, but does not significantly enhance parameter understanding beyond the schema.

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 uses a specific verb ('ask') and identifies the resource (TOP preview image), clearly stating the purpose. It distinguishes this from the sibling `caption_top` by noting that copilot_vision always routes through the vision model with a custom question, whereas `caption_top` 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 provides clear context for when to use this tool, including prerequisites (LLM backend) and a comparison with the alternative `caption_top`. It does not explicitly state when not to use it, but the differentiation is sufficient for selection.

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