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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds one genuine behavioral trait beyond that — the figure is non-binding and final prices depend on site approval. That caveat is useful, but the description says nothing about what the response contains (a total, a breakdown per item, currency) or how kind-specific parameters combine, which matters for a 7-parameter pricing tool.

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 short sentences, front-loaded with what the tool produces, with zero filler. The second sentence is a caveat rather than a definition, but it still earns its place by warning that the number is not contractual.

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?

Only one parameter is required, but five others are conditionally relevant depending on kind, and the description never signals that the caller must supply kind plus kind-specific fields. The schema covers most of this gap (content_item and quantity say which kind they belong to), but plan and pr_item carry no such note in either place, so the definition is only adequate for a tool of this branching complexity.

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 description coverage is 71% and the enum descriptions are unusually rich — the kind enum spells out each product line and its pricing, addons explains credit consumption, credits and quantity state their constraints. The description adds nothing to any parameter. With coverage near the high band, the schema does the work and a 3 baseline is appropriate.

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 identifies a specific resource (an order's price) and a specific purpose (an indicative figure produced before purchase), which separates it from place_order. It never names either sibling, so the agent has to infer that get_catalog and place_order are the other options rather than being routed explicitly.

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?

'before placing it' implies the pre-purchase context and therefore an ordering relative to place_order, but there is no explicit "use this when… use X instead when…" statement. No prerequisites, no mention of what to do with the returned figure, and no exclusion cases.

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