get_sources

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

With no annotations, the description needs to disclose behavior. It conveys that the operation is read-only (retrieving cached data) but does not mention edge cases like invalid or expired session IDs, potential staleness of cached sources, or whether it triggers any underlying actions. The word 'cached' adds some context but not enough for a higher score.

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 concise sentence, front-loaded with the action and resource. No wasted words, and it directly states the tool's function.

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 simple single-parameter retrieval tool with an output schema, the description provides sufficient context about input and purpose. It could mention behavior on invalid session or staleness, but those are edge cases, and the overall completeness is adequate.

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 provides 100% coverage with a clear description of session_id. The tool description essentially repeats the schema's 'previous web_search session_id', adding no new meaning. Baseline 3 applies given full schema coverage.

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 clearly states a specific verb ('Retrieve') and resource ('cached sources') tied to a previous web_search session_id. This distinguishes it from sibling tools like web_search or web_fetch, which perform live operations.

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 clearly implies usage after a web_search by referencing 'previous web_search session_id'. However, it does not explicitly mention when not to use it or name alternatives, but the context is evident given the sibling tools.

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