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

Annotations only assert readOnlyHint and openWorldHint; the description goes far beyond by disclosing row masking, that only the niche filter applies to masked results, the per-row ref/reveal mechanic tied to monthly free reveals, and that paid-plan results consume monthly export rows (repeat brands free). These are exactly the quota and data-visibility facts an agent cannot infer from structured fields.

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?

Purpose and signal types are front-loaded, then plan/quota mechanics follow in order of decision relevance. It is dense—four long clauses covering masking, reveals, and export accounting—but nearly every clause carries decision-relevant information, with only minor redundancy in restating plan-gating already in the schema.

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 an 8-parameter, no-output-schema search tool, the description supplies the query defaults, the plan-gated filter boundaries, the masking/reveal path, and the cost model. An agent has everything needed to decide whether to call it, what it will receive, and what it costs.

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 already marks most filters as paid-plans-only, so the baseline is 3. The description adds value by stating the default signal behavior and that all of the caller's niches apply when omitted, plus the masked-result limit context implied by the limit field, though it does not elaborate on offset/paging semantics.

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 (search US ecommerce brands flagged for Meta ad signal changes) and enumerates the four signal types plus the returned fields. It also distinguishes itself from the sibling reveal_brand by explaining that masked rows carry a ref for unmasking, so an agent can tell the two apart without opening either 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?

Explains the default signal selection (new + scaling across the caller's niches), the masking condition when unauthenticated or on the free plan, and routes to reveal_brand for unmasking. It doesn't explicitly contrast with check_store or lookup_brand, so it falls short of naming when-not-to-use this tool, but the operative conditions are clear.

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