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

Beyond the annotations (readOnly, openWorld, non-idempotent, non-destructive), the description discloses rich behavioral details: status values (unavailable vs error), per-vendor webSearch behavior, meta_ai eligibility restrictions, and billing implications (operator keys, no credits spent). No contradictions 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?

The description is a single dense paragraph that front-loads the core purpose and then adds only high-value details (status semantics, webSearch variance, eligibility, billing). Every sentence earns its place.

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?

With no output schema and annotations covering only safety, the description must carry behavioral burden. It thoroughly explains statuses, model id reporting, and webSearch variation, but does not explicitly describe the overall response structure (e.g., array of results for each model).

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 100%, so the baseline is 3, but the description adds meaningful semantic detail for the webSearch parameter by explaining per-vendor support (You.com always grounded, grok honours it, others always false), which is not in 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 states a specific verb (runs a prompt) and resource (directly-verified vendor models), names the exact vendors, and explicitly distinguishes itself from the sibling explore_ai_prompt by contrasting persona labels with real vendor model ids.

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 names the alternative (explore_ai_prompt) and the condition that selects this tool (you want real vendor model ids rather than persona labels), but does not explicitly state when not to use it or give a full decision procedure.

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