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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description still adds real behavioral context: the ingest-observation floor that causes 'most sections have only one version and return diff: null'. It doesn't cover the format modes or any cost/pagination behavior, but the key failure mode (null diffs) is disclosed.

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?

Three tight blocks: purpose first, then the mode semantics, then the limitation and sibling routing. Every sentence carries distinct information; nothing is repeated from the title or schema.

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 5 params (1 required), an output schema present so return-shape explanation is unnecessary, and no annotations gap to fill, this description supplies what's missing: mode semantics, data-coverage limits, and sibling routing. The only residual hole (format options, date semantics) is minor for a diff tool.

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 description carries meaningful load for `mode`, explaining both enum-like values and their semantics; without this, the agent would have no way to know what 'pending' vs 'observed' means since the schema gives `mode` no description and no enum. However, `format`, `from_date`, and `to_date` remain unexplained in both the description and the schema (only coverage is on `citation`), so it doesn't fully compensate for the 20% coverage.

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 specific verb+resource+granularity: 'Word-level diff of a North Carolina (NC) statute section between two versions.' It further splits the operation into two named modes (pending vs observed), which is exactly the distinction an agent needs to pick this tool over get_statute or search_statutes.

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 explicit selection criteria for each mode ('what will change on 1 October' vs recorded versions between two dates) and names the alternatives with their conditions: 'For earlier change dates use amendment_history; for pending text use pending_changes.' Both when-to-use and when-not-to-use are covered.

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