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

Beyond the destructiveHint annotation, the description explains that it overwrites human-facing content, requires showing the candidate and obtaining explicit approval, and notes that hedged sentences and enrichment meta-commentary are stripped. This gives the agent a concrete understanding of side effects and safeguards, adding real value over the annotation.

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?

Every sentence earns its place: the core action, the clarification of the candidate source, the approval requirement, and the applicability threshold. It is front-loaded with the action and avoids redundancy, making it efficient to parse.

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 destructive write operation with an approval workflow, the description covers the essential prerequisites: the source of the candidate, the sanitization behavior, the approval requirement, and the condition for use. It does not specify the return value, but that is not critical for a one-parameter write operation without an output schema.

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?

The single parameter productId is fully described in the input schema (100% coverage), so the schema already carries the meaning. The description adds no additional semantics beyond referencing get_product as the source of the candidate, which is implicit from the purpose. Baseline 3 is appropriate.

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 uses a specific verb ('Replace') and resource ('one product's shopper-visible store description') and clarifies it uses the sanitized enriched version (storefrontDescriptionCandidate) rather than the raw agentDescription. It clearly distinguishes from get_product (which provides the candidate) and other enrichment tools, leaving no ambiguity about what the tool does.

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?

It provides a clear applicability condition ('Only applies when the store's current description is thin (<200 chars)') and a mandatory approval step ('MUST show the merchant that exact candidate first and get their explicit approval'). It does not explicitly name alternative tools, but the condition and approval requirement are sufficient to guide an agent's decision.

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