cross_reference_flakiness

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

With no annotations, the description carries the full burden for behavioral disclosure. It explains the scoring intent and the return value, but it does not disclose matching logic, edge cases, or any side effects. This is adequate but not rich.

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?

Two sentences, front-loaded with the task, no filler. Every word adds value and the structure is easily scannable.

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 moderate-complexity tool with two well-specified parameters and no output schema, the description covers the core return value ('probability scores per test') and enough behavioral context to use the tool. It could be more explicit about the matching key, but overall it is complete.

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 coverage is 100%, so the schema already fully documents both parameters and their fields. The description adds no meaningful parameter-level detail beyond what the schema provides, settling at the baseline of 3.

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 uses a specific verb ('score') and names the exact resource ('test failures' and 'flakiness history'), clearly distinguishing this tool from siblings like aggregate_suite_failures or correlate_code_changes. It also states the distinguishing outcome: separating flaky tests from real regressions.

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 clearly states the required inputs ('Given a list of test failures and a flakiness history'), providing clear context for when to use it. It does not explicitly mention when not to use it or name alternatives, but the prerequisites are obvious enough.

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