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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is partly carried; the description adds genuine value beyond that by scoping the side effects ('records operational information and creates no accounting bill/payment') and by disclosing token invalidation on changed/expired records. Minor blemish: 'omitted optional fields are cleared' refers to fields that do not appear in this tool's schema (only the token is accepted), which could briefly mislead an agent about what it is passing.

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?

Dense and largely front-loaded, but the ordering is uneven: the replacement semantics ('flat amount or rate per ton with tonnage') land after the token mechanics, and the closing 'Requires confirmation' restates the opening sentence. Trimming that redundancy and moving the 'what it changes' clause forward would tighten it without losing information.

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 single-token confirmation tool with no output schema, the definition covers the important ground: what gets replaced, that omitted fields are cleared, that no bill or payment is created, and that stale tokens require re-preview. Only the eventual return value (what an agent gets back after applying) and token lifetime details are unstated, both minor given the preview/apply contract.

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 reported as 0%, so the description must carry the token semantics, and it does: the token is the sole accepted input, must be the exact value returned by this operation's preview, and must be used only after user confirmation. It does not document token format, length, or reuse/consumption behavior, which leaves a small gap.

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 states a concrete verb+resource pair: replace a load's saved revenue using either a flat amount or a rate-per-ton with tonnage, and it explicitly positions itself relative to preview_set_load_revenue. It is slightly muddled by the leading 'Apply only the exact change...' framing, which describes the token mechanism before the actual effect, but an agent can still tell what this tool does and that it is not the preview tool.

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?

It gives an explicit precondition (only after the user confirms the preview returned by preview_set_load_revenue), an explicit input restriction ('accepts its confirmation_token only'), and an explicit failure path ('changed or expired records require a new preview'). This is exactly the when/when-not/alternative coverage that makes the preview-then-apply pair safe to drive.

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