get_index_sources

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

No annotations are present, so the description carries the behavioral disclosure burden. It does disclose key behavior: aggregation across every LLM response and ranking by citation frequency. However, it leaves out practical details such as whether the list is limited to top domains, pagination, or the exact shape of the response, which are relevant because there is no output schema.

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 one sentence with an em-dash clarification and contains no filler. The verb, resource, scope, and ranking criterion are front-loaded, so an agent can parse the purpose immediately.

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 single-parameter read-style tool, the description covers the main invocation need: what is returned (domains), the ordering (by citation frequency), and the scope (every LLM response in the index). With no output schema, it could have specified the result format more explicitly, but no critical selection or invocation cue is missing.

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 has 100% coverage for the single parameter: indexId is described as the index UUID from list_indexes. The description adds no new parameter detail, but the schema fully carries that responsibility, putting this at the baseline of 3.

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 and resource: it returns domains ranked by citation frequency across every LLM response in the index, and the trailing clause explains what that means in intent terms. It does not explicitly distinguish this from sibling tools like get_index_results or get_index_share_of_voice, so it stops short of a 5.

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 a use case ('which sources the AI engines lean on most') and clarifies the scope (across every LLM response in the index), but it never states when to prefer this tool over the other index-related siblings or when not to use it. There is no explicit alternative routing.

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