Log Run

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

Annotations already declare it is a non-read-only, non-destructive, closed-world write. The description adds genuinely new behavioral context: the write is to a local file on this machine, nothing is transmitted externally, and the stored data is later consumed by estimate_time. It does not cover idempotency or duplicate-run behavior, which the false idempotentHint implies matters.

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 short sentences, front-loading the action and its effect, with the privacy guarantee last. Every clause carries information and there is 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?

With an output schema present and full parameter documentation, the description only needs to establish purpose, destination, and privacy, which it does. Minor omissions remain around duplicate handling and whether timing at least one of seconds/promptfoo_results must be supplied.

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 description coverage is 100% with each of the 8 parameters documented, including the way/model/tokens/promptfoo_results fields, so the baseline is 3. The description only echoes the promptfoo results-file mode, adding no syntax, format, or default-behavior detail beyond the schema.

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 states a concrete verb and resource: persist a timed run (or every result of a promptfoo results file) to a local file. It also names the consumer sibling (estimate_time), which helps orient the agent, though it does not contrast itself against other siblings such as estimate_cost or compare_models.

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?

Usage is implied: call this after a model call, or when you have a promptfoo results file, to feed the timing estimator. There is no explicit when-not guidance or named alternative for capturing run data differently, so the agent must infer the trigger conditions.

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