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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: results are deterministic (reproducible for the same inputs) and the tool performs no payment, profiling, or final-tax computation. It does not disclose how recommendations are ranked, whether results can be empty, or why determinism matters to the caller.

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 tight sentences with no filler, front-loading the core operation before the exclusions. The density is slightly cryptic ('direct/quote preference' vs. the schema's 'purchase'), but nothing is wasted.

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 six-parameter tool with no output schema and 17% schema coverage, an agent still lacks essentials: what a result looks like (ranked offers? count bounded by limit?), and how the enum options change behavior. The boundary statements are helpful, but the definition is only minimally sufficient to invoke 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?

Schema coverage is only 17% (just 'goal' is documented), so the description must carry the load, and it does mention four of six parameters by concept: goal, budgetUsd, delivery, and purchase preference. It does not explain the enum values for delivery (digital/human/any) or purchase (direct/scope/any), nor the unseen 'limit' and 'language' parameters, leaving meaningful gaps.

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 action and resource: 'Deterministic public offer matching by a short business goal, optional USD budget, delivery kind and direct/quote preference.' An agent can tell this is a recommendation/matching operation over public offers, distinct in spirit from detail or purchase-link siblings. It stops short of naming the closest siblings (acorn_find_offers, acorn_compare_offers), so the differentiation is inferred rather than stated.

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?

Usage is only implied by the inputs (goal, budget, delivery, preference); there is no explicit 'use this when' statement. With three closely related siblings (find, compare, details) available, the description gives no rule for choosing between recommendation, search, and comparison. The negative constraints ('no personal profiling, payment or final-tax calculation') describe scope limits rather than routing guidance.

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