analyze_failures

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

Annotations already provide readOnlyHint, idempotentHint, and destructiveHint. The description adds behavioral context by requiring an explicit filtered cohort and indicating it is meant to follow list_runs. This goes beyond the annotations without contradiction.

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 a single sentence that packs essential information: action, resource, read-only nature, and workflow context. It is concise with no 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?

While output schema and annotations are present, the description does not clarify what 'analyze' produces (e.g., statistics, list of failures) or what constitutes a 'failure' (execution_status vs validation_status). This ambiguity leaves some gaps for such a complex tool.

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 descriptions are completely absent (0% coverage), and the description only vaguely refers to an 'explicit filtered' cohort without explaining the filter fields or the role of the required 'limit' parameter. This does not sufficiently compensate for the lack of schema descriptions, especially given the complexity of the RunFilter object.

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 specifies the action ('Analyze'), the resource ('explicit filtered failure cohort'), and the mode ('read-only'), which distinguishes it from sibling analysis tools like analyze_hotspots and analyze_memory. Adding 'after list_runs discovery' provides workflow context, making the purpose unambiguous.

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 a clear usage context: use after list_runs discovery, and the phrase 'explicit filtered failure cohort' implies a filter is needed. However, it does not explicitly mention when not to use it or name alternative tools, so it falls short of a 5.

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