find_exceptions

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

No annotations are provided, so the description carries the burden. The 'Find' verb implies a read-only operation with no destructive side effects, and the error status filter is stated. However, it does not disclose other behavioral traits such as filtering behavior, pagination, or how errors are identified. The output schema covers return values, but this is partial transparency.

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 sentences, front-loaded with the main action and an explicit alternative. Every word earns its place, and there is no redundancy or irrelevant information.

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?

The description is too terse for a tool with four parameters, no schema descriptions, and no annotations. It fails to explain parameter semantics or mention other relevant sibling tools like get_error_count or fetch_observations, which could be alternatives for error-related queries. The output schema exists, but the description alone is insufficient for confident invocation.

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 description coverage is 0%, and the description mentions none of the four parameters (limit, project, from_timestamp, to_timestamp). It adds no meaning beyond parameter names, forcing the agent to guess their roles. This is a critical gap given the schema provides no descriptions.

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's function: 'Find observations with error status.' The verb 'Find' and the specific resource 'observations with error status' make the purpose unambiguous. It also distinguishes itself from detect_failures by pointing to that tool for LLM output quality issues, which helps differentiate among siblings.

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 explicitly provides an alternative tool and a when-not-to-use scenario: 'Use detect_failures for LLM output quality issues instead.' This gives the agent direct selection guidance, meeting the criteria for explicit usage guidelines.

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