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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description adds real behavioral context beyond them: nothing is persisted, `secrets` run empty (only names are passed), script executes as a SolidPing worker, fetch returns status/headers/first 16 KB, browser returns a selector-annotated tree, and the mcp:read token scope. These are the failure modes an agent would otherwise hit blindly.

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?

The key point — dry-run before create_check, nothing saved — is front-loaded in the first sentence, and each following clause maps to a distinct parameter concern. It is dense rather than padded, though the semicolon-chained prose for the three kinds is a touch heavier than needed.

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?

An output schema exists, so return values need not be spelled out, yet the description still previews status/output/metrics per kind. With annotations covering safety, six parameters fully documented, and the secret-handling caveat surfaced, nothing an agent needs to call this correctly is missing.

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%, so baseline 3 applies, but the description adds genuine nuance the schema only partly carries: `env` is plaintext while `secrets` only names parameters that execute empty — a distinction that changes how the agent should compose a call. The kind-mode behaviors are restated in prose rather than adding much new beyond the enum descriptions.

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 — explore a target and dry-run a js check — and immediately scopes it as a non-persisting precursor to create_check. The three `kind` modes (script/fetch/browser) are named inline, so an agent can distinguish it from create_check, run_check, and validate_check without opening the 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?

Gives a clear when: test a check before create_check, without saving anything. That establishes the main alternative and the condition that selects it. It does not explicitly exclude the other near-siblings (validate_check, run_check, diagnose_check), which would be the only thing separating a 4 from a 5.

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