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

Annotations already indicate readOnlyHint=false and openWorldHint=true, so the tool is known to have external effects. The description adds crucial context: it calls external providers directly and caps each invocation at 30 provider calls, making the scope and safety boundary explicit. It does not detail failure modes, auth, or cost beyond the cap, but the provided behavior is meaningfully transparent.

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 contain all essential information: purpose, user-approval precondition, external calls, and invocation cap. The critical guardrail is stated immediately after the purpose, and there is no filler or redundancy.

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 side-effecting external-call tool with no output schema, the description covers purpose, approval requirement, external nature, and batching bounds. It does not describe the result format, but the purpose statement—collect reliability, quality, latency, and cost evidence—already implies the expected output. Minor gaps in operational detail are acceptable given the other structured schema fields.

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 60%, so the description does not need to carry the full parameter burden. It adds useful context by explaining the task set is a curated URL set and that invocations are capped at 30 provider calls, which maps to maxCalls. However, it does not clarify repeats or provider selection behavior, and the schema already documents taskIds, providerIds, and confirmExternalCalls.

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 opens with a specific action—'Benchmark web-extraction vendors'—and names the resource and scope: a curated URL task set collecting reliability, quality, latency, and cost evidence. This clearly distinguishes calibrate from the billing/recommendation siblings, which perform entirely different functions.

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 description gives an explicit precondition: use only after the user explicitly approves a bounded calibration batch. It also warns that the tool calls external providers directly, which informs risk assessment. It does not name specific alternatives or when-not-to-use conditions, but the sibling tools are unrelated and this contextual guidance is clear enough.

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