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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds genuine behavioral context beyond them: the output is plain-language, the tool is one-coverage-per-call, and it cannot adjudicate policy-specific claim coverage.

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 sentences, front-loaded with the usage trigger, no filler. Each sentence adds a distinct fact: when to use, what it returns, and what it cannot do.

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?

There is no output schema, but the description compensates by stating the return form (plain-language explanation) and the tool's boundary condition. For a single-enum-parameter read tool, an agent has everything needed to call it correctly.

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 100% and the enum even documents synonym mappings (GL = general liability, etc.), so the schema carries the detail. The description still adds the calling-unit semantics ('once per coverage'), clarifying that multi-coverage questions require multiple calls.

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 action (explain) on a specific resource (a commercial insurance coverage) and scopes it to a single coverage type per call. It is clearly distinguishable from siblings like suggest_coverages and classify_business, which do different jobs.

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 an explicit trigger ('when the user asks what a commercial insurance coverage is or how two coverages differ'), an invocation pattern ('call it once per coverage'), and an exclusion ('cannot tell whether a specific policy covers a specific claim'). Nothing about when to use or avoid it is left to inference.

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