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

Annotations already cover safe-read semantics (readOnlyHint, idempotentHint, destructiveHint=false), so the bar is lower. The description still adds real value: it clarifies no purchase occurs, that results include links to continue on trimcarbon.com where signup/payment happens, and that pricing comes in whole-tonne increments with monthly and yearly plan variants.

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?

Four tight sentences, front-loaded with what is returned before the scope caveat and the usage condition. Every sentence carries distinct information: return shape, the outbound links, the no-purchase boundary, and the trigger condition.

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 present, the description need not enumerate return fields, and the annotations already establish it as a safe read. What remains valuable — that no transaction occurs and that the user completes signup on trimcarbon.com — is stated. It is complete enough, though it could note that inputs are usually fed from an estimate tool, which it only implies indirectly.

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 100%, so all four parameters (kg, hours, period, aircraft) are already documented in the schema. The description hints at the year/total distinction via 'for yearly amounts the monthly and yearly plans,' but adds no syntax, units, or format detail beyond what the schema provides, so the baseline of 3 applies.

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?

States a specific verb and resource: returns TrimCarbon's pricing to offset a given amount of CO₂, broken into one-time purchase and monthly/yearly plans. This clearly separates it from the sibling estimate_* tools (which compute emissions) and the get_certificate/list_my_offsets tools (which retrieve existing purchases).

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 an explicit usage condition ('for when the user asks what offsetting costs') and an explicit negative boundary ('This tool does not buy anything'), which prevents an agent from misusing it as a purchase action. It does not name a sibling alternative for the actual sign-up/purchase path beyond pointing at trimcarbon.com, so it falls just short of full when/where routing.

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