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

Annotations already declare a safe read-only, closed-world operation, so the description's job is to add context beyond that. It does: it discloses that rates are reported with their sample size and that a supplier with no history is labeled 'unknown' rather than ranked favorably — an important interpretive rule an agent could not infer. It does not discuss cost of broad queries or result ordering, but for a read-only comparison the transparency is strong.

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 verb and the comparison dimensions, with the conditional item behavior placed after the core statement. The parenthetical of term examples is dense but informative. Minor cost: the em-dash clause is long and slightly harder to parse than a plain sentence.

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 no output schema, the description carries the burden of explaining what comes back, and it does so concretely (terms, on-time/fill rates plus sample size, item price, unknown handling). For a two-optional-parameter read-only tool this is close to complete; only result ordering and behavior when suppliers is empty are unspecified.

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 baseline is 3, but the description adds genuine meaning: the item parameter's effect (item price shown only when an item is supplied) and the implicit fact that suppliers is a scoping filter rather than a requirement, since comparison can run across all suppliers. That conditional semantics is not in the schema.

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 opens with a specific verb and resource ('Compare suppliers') and enumerates exactly what is compared: general terms, measured on-time and fill rates with sample size, and per-item current price. An agent immediately knows the tool's output content. It stops short of naming a sibling, so the boundary with tools like proc_item_explain or fin_scenario_compare must be inferred.

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 implied rather than stated: the phrase 'when an item is given' signals that passing an item broadens the comparison to include pricing, which is real conditional guidance. There is no explicit when-to-use or when-not-to-use statement, and no named alternative for narrowing to a single supplier.

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