get_run_error_clusters

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

With no annotations provided, the description must carry the behavioral burden. It discloses that the tool 'surfaces clusters of tests sharing the same root-cause error' and supports filtering by status. This gives the agent a clear understanding of the analysis behavior without side effects or safety details, which are not needed for this read-only grouping operation.

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 three sentences, each with a distinct purpose: (1) states the main function, (2) gives usage context with a preceding tool, and (3) explains the optional filter and required parameters. No unnecessary words or redundancies.

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 tool has 3 parameters, no annotations, and no output schema. The description covers the purpose, workflow (after list_testruns), and parameter constraints (requires projectId and testrun_id). It also implies the output (clusters of tests by error signature). This is sufficient for moderately complex tool, though it does not describe pagination or result size, which could be helpful.

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 already provides 100% parameter descriptions, so the baseline is 3. The description adds a brief note about the status filter meaning ('failed' shows definitively failed tests, etc.), but this mostly restates the schema's enum descriptions. No additional syntax or format details are provided.

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: 'Groups failing tests in a run by error signature to identify patterns and triage failures at scale.' This specific verb+object+goal distinguishes it from sibling tools like get_run_details or debug_testcase, which address different aspects of test runs.

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 says 'Use this after list_testruns to drill into why a run failed,' providing clear workflow context. It also explains the status filter, but does not explicitly mention when NOT to use the tool or name alternatives beyond the sequential dependency.

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