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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so 'Read-only: nothing is stored' largely restates structured data. The genuinely additive disclosure is 'Fast; no model call', which tells the agent there is no LLM latency or cost — useful, but a single trait. Nothing is said about result ranking, empty-result behavior, or passage truncation.

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 sentences, zero filler. The content scope and return value lead, and the operational traits ('Fast; no model call', 'nothing is stored') are packed into the trailing fragments rather than a separate paragraph.

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?

For a two-parameter read-only retrieval tool with rich annotations and no output schema, the description covers what it searches, what it returns, and its cost profile — enough to call it correctly. The remaining gap is query formulation guidance for the undocumented required parameter, which is the one thing an agent could get wrong.

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 only 50%: 'limit' is documented (default 6, range 1–10) in the schema, but 'query' has no description anywhere. The tool description does not clarify whether query is natural language, keywords, or a citation fragment, nor does it mention the limit parameter at all, so it fails to compensate for the coverage gap on the one required parameter.

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?

The description gives a specific verb (search) and resource (HenryKnows' knowledge base) and even enumerates the content domains — regulations, SEVP/USCIS guidance, Federal Register rules — plus what the agent gets back (matching passages with source links). It implicitly separates itself from ask_henry via 'no model call', but never names the sibling explicitly, so the differentiation 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?

The clause 'so you can read and cite the text yourself' plus 'Fast; no model call' clearly signals the use case: raw, citable passages rather than a synthesized answer from ask_henry. It stops short of an explicit when-not rule (e.g., 'use ask_henry instead when you want a summarized answer'), so the routing decision is left partly to inference.

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