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

Annotations are readOnlyHint=true and openWorldHint=true, but the description adds critical behavioral context: catalogSize/catalogVisibility are 'reported here only when already known' and 'never waits on the item count'. It explains null semantics and that they are not interchangeable, and warns against misinterpreting null. No contradiction with annotations.

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 description is 5 sentences, front-loaded with what the tool returns and key use cases. It is content-rich without being verbose. Minor improvement could be combining the last two sentences about null handling, but overall it's well-structured and efficient.

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?

Without an output schema, the description covers all expected return fields (fee bands, minimum order, service area, provenance) and explains edge cases (null values for catalogSize/catalogVisibility). It also references a sibling tool for when a reliable count is needed. This is complete for an AI agent to understand and use the tool 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?

Only one parameter (service_slug) with 100% schema coverage. The description adds extra context: 'Take the slug from a plan's serviceSlug' and provides an example ('shufersal-online'). This gives the agent explicit guidance on how to source the parameter value, going beyond the schema's description.

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?

Description clearly states the tool returns 'full published terms for a single online storefront' including specific details (fee bands, minimum order, service area, provenance). It distinguishes from siblings by specifying it's for a single storefront and gives example use cases like explaining a deliveryFee from optimize_delivery. The name is also clear.

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?

Explicit guidance: 'Use to explain a deliveryFee an optimize_delivery plan reported, or to answer what do I need to spend for free delivery?' It also tells when not to use it (e.g., never read a null as an empty shop) and directs to list_delivery_options for a reliable count. This clearly differentiates from siblings.

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