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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's job is to add semantics — and it does, by disclosing the three-valued outcome and the rule that missing inputs produce 'uncertain'. That is exactly the non-obvious behavior an agent needs. It does not describe cost, latency, or what the verdict payload contains, but an output schema exists to cover the latter.

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, front-loaded with the purpose and then the uncertainty rule. Every clause carries information — the factor list doubles as a checklist of what to supply — with no restatement of the title or filler.

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?

With an output schema, full parameter coverage, and rich annotations, the description covers the remaining gaps: purpose and the semantics of partial input. What is missing is only the workflow position — whether to call this before presenting an offer and what to do when the result is 'uncertain'. That is a modest omission for a 9-parameter evaluation tool.

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%, so the baseline is 3; the description goes beyond it by generalizing the 'unknown if omitted' rule to all nine inputs, whereas the schema only states 'Omit if unknown' for memberships. It also frames order_total as a minimum-spend input, adding intent beyond the field label. It adds no format or unit detail for country beyond what the schema already gives.

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 names a specific verb and outcome ('Evaluate whether a shopper can get an offer's price') and enumerates the exact eligibility dimensions considered (memberships, location, channel, first order, coupon clipping, Subscribe & Save, order total). This is far more specific than the bare title 'Check eligibility' and is distinguishable from read-oriented siblings like get_offer or get_price_context. It stops short of explicitly naming which sibling to use instead, which keeps it from a 5.

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 gives clear invocation context: pass whatever you know about the shopper, and any omitted fact degrades the verdict to 'uncertain' rather than a false 'eligible'. That is actionable guidance about how to call the tool well. It does not discuss when to prefer verify_offer or get_price_context, so alternatives are left implicit.

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