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

Annotations already declare openWorldHint=true, non-idempotent, non-destructive, so the bar is lower. The description earns credit beyond that by describing the side effect concretely (a shareable link, pre-filled checkout the customer pays on) and the consent/condition-disclosure obligations; it does not mention that repeated calls create duplicate baskets, which matters given idempotentHint=false.

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?

Front-loaded with the create-and-get-a-link outcome, then prerequisites and constraints. Four sentences with little waste, though the graded-units sentence is dense and assumes familiarity with basket_link's rules rather than restating them.

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 6-parameter, nested-object creation tool with no output schema, the description covers the outcome (link), the prerequisite tool call, and the consent/disclosure rules. Gaps are link lifetime/expiry, duplicate-call behavior, and what happens if the date is not one check_delivery offered.

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?

With 67% schema coverage, the schema already documents most fields. The description adds genuine meaning by pairing the two item arrays with their intent (NEW items vs GRADED units) and by tying delivery.date to check_delivery's offered dates and condition_shown_to_customer to graded_ids. It says nothing about comment or which fields are realistically mandatory for a payable checkout, leaving the 'required: 0' schema misleading.

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?

A specific verb+resource: 'Create a shared basket with the items AND the customer's contact and delivery details ... and get a link', followed by what the customer experiences. It is clear what the tool produces, but it never explains how this differs from the sibling basket_link beyond invoking the same rule for graded units, which is the key ambiguity for an agent choosing between them.

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 real prerequisites: 'Use check_delivery first for valid dates', show grade/condition notes/photos before setting condition_shown_to_customer, and 'Only use the customer's real details, with their agreement'. Clear context but no explicit exclusion or statement of when basket_link should be used instead.

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