run_index_prompts

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

No annotations are present, so the description must carry behavioral disclosure. It does disclose the core side effect: it runs prompts and stores full per-LLM results. However, it does not mention whether runs are idempotent, whether existing results are overwritten, how long or costly the operation may be, or what the caller receives back.

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?

Two sentences with no flf filler. The main action and scope are front-loaded, and the 'No brand filter' clarifier is efficient and purposeful.

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 one parameter and full schema coverage, the description is mostly adequate, but without an output schema or annotations it leaves important gaps for a side-effectful execution tool: it does not point to how results are retrieved afterward (e.g., get_index_results) or warn about long-running/cost implications.

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?

The schema already fully describes the single parameter indexId as 'The index UUID from list_indexes' (100% coverage). The description adds no parameter-specific meaning beyond that baseline.

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: 'Run all prompts in an index'. It further differentiates by scope: 'across all 4 LLMs' and the explicit exclusions 'No brand filter — every entity mentioned is captured'. This clearly distinguishes it from siblings like run_brand_prompts.

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 gives implied usage context by saying there is no brand filter and that every entity is captured, which suggests this is the unfiltered, index-wide execution tool. However, it never explicitly names an alternative such as run_brand_prompts or states when this tool should not be used.

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