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

Annotations already declare the safe read-only, idempotent profile, so the bar is lower; the description still adds real context by listing what is returned (line items, commission band, payment timing, exclusions) and the key caveat that it is an estimate not a quotation and that >100 km travel is flagged rather than priced.

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?

Three tight sentences, front-loaded with the computation performed, then outputs, then the estimate/scope caveat. Each sentence carries distinct information with no 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 no output schema, the description usefully enumerates the return contents and the estimate/flagging caveats, which is enough to call a stateless calculation tool correctly. The one gap is the unresolved relationship to get_pricing.

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 the schema already explains each of the six inputs with examples (man-days, SKU counts). The description adds no per-parameter meaning beyond what the schema provides, making the baseline 3 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?

States a specific verb (estimate/arithmetic) and resource (fees from published rates) with scope: per-job checks and/or commission for an order value. Clear and distinct in function, but it never names or differentiates itself from the sibling get_pricing, which an agent could easily confuse it with.

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 by the mention of order value and per-job checks, so an agent can infer it is for producing a fee estimate. However, there is no explicit when-to-use vs get_pricing, nor any stated prerequisites or exclusions guiding selection between the two pricing-related tools.

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