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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the description is not obligated to restate them. It does add real behavioral value beyond them: it discloses the result cap ("up to 5 answers"), that answers carry citations "where one exists," and critically what an empty result means — the approved sources do not cover the question. That negative-result semantics is the kind of context annotations cannot provide.

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 tightly packed sentences, front-loaded with the verb and resource before the topical parenthetical and the return semantics. The parenthetical topic list is long but earns its place by letting an agent route on subject matter. Minor density cost, no filler.

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 no output schema, the description must carry return-value information, and it does at a useful level of detail: up to 5 answers, each with citation when available, plus empty-result meaning. What is missing is answer formatting and whether results are ranked or deduplicated, which matters for a search tool but is a modest 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?

Schema coverage is 50%: query is documented ("The question or topic, in plain words.") but limit has no schema description. The sentence "Returns up to 5 answers" indirectly explains the limit's ceiling and intent, which partially compensates, but it never states the parameter's role, default, or that fewer results than the limit may come back.

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 ("Searches") and a specific resource ("The Comp Desk's approved knowledge base of New York workers' compensation questions and answers"), then enumerates covered topics (benefits, permanency, IMEs, Section 32, labor market attachment, Board procedure, forms). It is clear what corpus is being hit, though it never contrasts itself with siblings like search_case_law or get_explainer, so the boundary is inferred rather than stated.

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 topic list and by the phrase "approved knowledge base" — an agent can infer this is for plain-language Q&A rather than statutory text. But there is no explicit when-to-use or when-not-to-use guidance and no named alternative for the adjacent tasks this tool sits among (case law search, term definitions, explainers).

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