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

Goes far beyond the annotations: quota accounting (1 per unique citation, max 50, min 1, deducted before the run), no refund on stopped_early, database outage yields cannot_verify while sections still get checked, non-Pro rejected before deduction, and the distinction between timeout errors (already charged) and queue errors (not charged). It even warns that not_found is not proof of a fake citation. Minor tension: idempotentHint=true while each re-run consumes quota again, but that is metering rather than resource mutation, so it is not a hard 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?

Front-loaded with purpose, then the Pro gate, then the verify_citation alternative, then cost and result semantics in short line-per-idea blocks. It is long, and the enumeration of the 21 resolved law codes reads more like reference material than selection guidance, but nearly every line carries operational value for a high-stakes tool.

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 complexity, an output schema, and quota consequences, the description covers everything an agent needs: which statuses exist and what each means, retry policy (retry only the individual item, never resend the whole document), truncation/nesting flags (unique_citation_limit_exceeded, stopped_early, extractor_capped), and a privacy warning on evidence_snippet.

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?

There is a single required parameter and schema coverage is 100%; the schema already documents the 1–50,000 character bound and that empty/oversized input is rejected before the Pro check and before quota deduction. The description reinforces

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 and resource (batch-audit every section/ruling citation in a single document) and lists the document types it applies to. It also draws a crisp line against the sibling verify_citation, so an agent can pick between them without opening either schema.

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?

Explicit routing rules: single citation → verify_citation (any package, any law in the corpus); unresolved law name → call verify_citation yourself with a known law_code. It also states the Pro-only gate up front, so the agent knows when this tool will be rejected.

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