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

No annotations are provided, so the description carries the full burden and meets it well. It discloses the exact counting categories, the non-summation rationale, same_as cluster behavior, determinism, and the absence of a model call—far beyond a typical tool definition.

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 front-loaded with the core quantity, and every sentence adds a distinct piece: definition, count types, non-summation rationale, cluster scope, distinction from citation count, and computational cost. No filler or 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 the metric's meaning, scope, determinism, and distinction from sibling tools. There is no output schema, and the description does not state whether the response returns both counts separately or in a particular shape, which is a minor but real gap.

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?

The schema fully documents run_id but leaves claim_id as just a required string with minLength. The description compensates by explaining that claim_id identifies a claim whose same_as cluster is counted, adding real semantic meaning 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?

States a precise metric ('how much the graph leans on a claim') rather than a vague 'returns significance'. Defines sub-quantities (leaned_on_by, contested_by) and explicitly distinguishes itself from a citation count, which separates it from the sibling methodist_citations.

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?

Gives clear context: counts incoming support/extend vs refute/qualify and notes that counting happens across the same_as cluster. The explicit 'NOT a citation count' acts as a de facto exclusion, steering the agent away from the citation-count sibling, though it does not phrase an exact 'use when' imperative.

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