what_matters

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

Annotations already provide readOnlyHint: true, destructiveHint: false, idempotentHint: true, so the safety profile is clear. The description adds behavioral details: auto-alignment of frequencies to avoid inflated n-counts, confidence labels, reason strings, and sharpen-suggestions. No contradiction.

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 with a headline structure. Every sentence provides essential information: purpose, auto-selection behavior, return format, and usage guidance. No wasted words.

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?

Given the tool's complexity (ranking, auto-selection, frequency alignment), annotations cover safety, and description covers purpose, usage, and return format. No output schema but description sufficiently details output (ranking with confidence labels, reasons, sharpen-suggestions). Complete for agent invocation.

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 75%. Description adds meaning: clarifies that if 'candidates' is omitted, auto-selection occurs based on same topic and entity_type. For 'outcome' and 'entity', it implies their roles but doesn't detail syntax. Adds value beyond 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 the tool ranks which metrics best explain an outcome metric for an entity, using specific verbs ('rank') and resources ('other metrics'). It explicitly distinguishes itself from the sibling tool 'find_drivers' with a clear use-case differentiation.

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 explicit guidance: 'Use this instead of find_drivers when you want a narrative-grade answer.' Also explains when candidates can be omitted (auto-selection from ontology) and mentions frequency alignment, giving clear context for when to use this tool.

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