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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine context beyond them: cases are pulled and KeyCited in Westlaw before approval, and only results from here carry that guarantee. It says nothing about result limits, pagination, or what happens when nothing matches.

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?

One front-loaded sentence opening with the verb and resource, followed by a colon-delimited list of returned fields, then a closing scoping sentence. Every clause carries information; the parenthetical court list and the record-field list are dense but purposeful.

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?

No output schema exists, and the description compensates by enumerating the returned fields (case name, citation, court, date, holding, summary), which is exactly what an agent needs. The main remaining hole is limit behavior and result-count expectations, minor for a simple read-only search.

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 50%: query is documented in-schema with two example formulations, while limit (1-5) has no description in either place. The description adds no meaning about how results are capped or what limit controls, so it neither compensates for the gap nor adds beyond the schema. Baseline 3 applies at this coverage level.

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?

Specific verb and resource with explicit scope: 'approved library of New York workers' compensation decisions (Court of Appeals and Appellate Division)', plus an enumeration of what each record contains. It stops short of naming a sibling such as search_wc_knowledge, leaving the agent to infer the distinction from 'Only cases returned here are backed by this source'.

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?

Usage is implied by the domain framing (case-law lookup) and by the provenance note that only this tool returns KeyCited-verified decisions, which hints at when to prefer it. No explicit when-not conditions and no named alternative, so the comparison with search_wc_knowledge is left to the agent.

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