get_evaluation_summary

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

With no annotations, the description carries the burden of behavioral disclosure. It states 'Read-only,' which is a key behavioral trait for an AI agent. However, it does not describe potential errors, authentication requirements, or what happens with an invalid run_id, leaving some transparency gaps.

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 two short sentences, front-loaded with the core action ('Return...') and immediately clarifies read-only status. Every word contributes value, with no redundancy or filler.

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?

Given the tool's low complexity (one optional parameter) and the presence of an output schema, the description is mostly complete. It covers the primary behavior and safety profile, though it could briefly clarify what 'local' means or mention the optional run_id in the description itself for standalone completeness.

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 input schema provides only a parameter name 'run_id' with no description. The description adds meaning by indicating the tool returns the 'latest' summary by default or a 'specified' one via run_id. This helps clarify the optional parameter's purpose, but it is not detailed enough to fully compensate for the 0% schema description 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 the tool returns 'the latest or specified local tool-selection evaluation summary,' which specifies both the verb ('return') and the resource. However, it does not explicitly differentiate from sibling tools like get_tool_metrics or get_audit_summary, though the resource itself is distinct.

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 usage through the 'latest or specified' phrasing, suggesting the tool is for retrieving evaluation summaries with an optional run_id. There is no explicit guidance on when to use this tool versus alternatives or any exclusions, leaving some ambiguity.

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