mureo_outcome_evaluate

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

Discloses all behavioral traits: deterministic calculation, directionality for metrics, noise band handling, and zero-baseline handling. With no annotations, the description fully covers the tool's behavior.

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?

Well-structured and concise despite length. Front-loaded with core purpose, each sentence adds distinct value without redundancy.

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?

Covers all aspects: purpose, inputs, behavior, edge cases, and integration with other features. No output schema exists, but description doesn't need return values as it's a pure calculation.

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?

Adds significant meaning beyond schema: explains 'before' is typically metrics_at_action, 'after' is current numbers, and describes the metric structure. For noise_pct, explains default and interpretation. Schema coverage is 100%, but description enriches understanding.

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?

Clearly states the tool evaluates whether an action outcome improved, regressed, or is inconclusive. Uses specific verbs and distinguishes from siblings by emphasizing deterministic calculation and cross-platform applicability.

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?

Provides context on when to use (to get a reproducible verdict instead of eyeballing numbers) and input requirements. However, does not explicitly state when not to use or compare to alternatives beyond noting it works for any platform.

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