benchmark_run

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

With no annotations provided, the description carries the full burden. It discloses that the tool records a run, that baseline sets a benchmark, and disallows model self-reports as measurementRef. However, it does not mention side effects, permissions, or whether the operation is read-only or destructive, leaving gaps in behavioral understanding.

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 with no fluff. The first sentence immediately states the purpose, and the second adds essential nuance. Every word earns its place, making it highly efficient.

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 tool with three required parameters, no output schema, and no annotations, the description covers the core idea but leaves out what constitutes a 'run', the nature of the 'frozen benchmark', and how hypothesis arms beyond 'baseline' are used. Additional detail on return values or side effects would improve completeness.

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 only 33% (only `arm` has a description). The description adds meaning for `arm` (baseline sets the bar) and `measurementRef` (must be a recorded raw artifact), but provides no additional info for `runId`. This partially compensates for the low schema coverage but is not comprehensive.

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 ('Record') and resource ('a tool-measured run of an arm through the frozen benchmark'), clearly distinguishing it from sibling tools like `benchmark_propose` or `benchmark_select`. The phrase 'tool-measured' and 'frozen benchmark' add precision.

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 states when to use 'baseline' as the arm and that `measurementRef` must be a recorded raw artifact, not a model self-report. This provides clear context for appropriate usage, though it does not explicitly list when-not conditions or compare directly with all siblings.

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