run_golden_set

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

No annotations exist, so description carries full burden. It details the comparison mechanics (numeric tolerance 1e-6, error-state matching) and return values (total/passed/failed, expected vs actual), which is substantial behavioral disclosure. Does not state whether it mutates state or requires specific session setup, but 'replay against live model' implies a non-mutating test run.

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 compact sentences: first defines the action, second defines output and purpose. 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?

Despite no output schema or annotations, description explains what the tool does, how it evaluates, what it returns, and the intended CI use case. For a 2-parameter tool, this is sufficient context; minor gaps like sessionId semantics are covered by the schema field name.

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?

Input schema covers path with a description but leaves sessionId undocumented (50% coverage). Description explains path as a golden-set file written by save_golden_set and adds context about re-evaluation, but does not clarify sessionId. Thus only partially compensates for missing schema info.

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?

States verb 'Replay' with resource 'golden-set file against the live model', clearly distinguishing from sibling save_golden_set and other model tools. Also specifies the evaluation and comparison purpose.

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?

Explicitly mentions the CI use case ('the numbers gate for verifying a measure change in CI'), providing clear when-to-use context. Doesn't explicitly name alternatives or exclusions, but sibling save_golden_set is the complement.

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