Choose AI models

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

Annotations already declare the write profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), so the safety baseline is covered. The description adds real value by disclosing the null-reset semantic and that the provider must already be connected, but it omits validation behavior (what happens with an unconnected provider or malformed string) and error responses.

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?

A single front-loaded sentence with the format rule first, then examples, then the reset instruction. No filler, and the Azure exception is placed inline where it matters.

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?

For a 5-parameter, optional-everything configuration tool with no output schema, the description covers the core contract: format, per-job slots, examples, and reset. The missing piece is the image-vs-vision distinction and the fact that unmentioned slots are presumably left untouched, which keeps it below a 5.

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 coverage is only 20%, with just the effort enum documented, so the description must carry the load. It gives format and examples for text, vision, and transcribe plus the Azure variant, but leaves the 'image' parameter entirely unexplained — notably it is not distinguished from 'vision', which is the main ambiguity an agent would hit.

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?

States a specific verb and resource: pick which connected provider and model handles each job, with the exact "provider:model" string format. The examples (anthropic:claude-opus-5-5, openai:gpt-5.5, groq:whisper-large-v3) and the Azure deployment special case make the operation unambiguous and clearly distinct from the read-only ai_status sibling.

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 does state one important usage rule: pass null to revert to the automatic choice, which tells an agent how to undo a setting. However, it never says when to prefer this tool over ai_status for inspecting current settings, nor whether changes apply only to future jobs.

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