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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses what the write actually does ('updates only an anonymous usage counter and does not verify an action') and gives a detailed data-handling profile: what arguments are stored, that account keys are one-way hashed, that billing/validation sources are not stored, and that no IP addresses are collected. This is substantive behavior the annotations do not convey.

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?

Front-loads the core action and the routing to the sibling before the privacy block. The data-handling sentences are dense and multi-clause but each carries relevant information, so only mild trimming is warranted.

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 and a mutation tool (readOnlyHint=false), the description supplies the necessary behavioral and data-retention context and defers parameter details to a mostly-covered schema. It is nearly complete; only finer details of the return/response side are unstated, which is acceptable given no output schema.

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 75%: service, billed_by, and step carry descriptions, and the outcome enum is mostly self-explanatory. The description restates the outcome categories but adds no syntax, format, or edge-case meaning beyond the schema, so a baseline 3 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 states a specific action and scope: counting a cancellation outcome (cancelled, kept_for_less, blocked, steps_changed) after the user reports it. It explicitly names the sibling report_action_outcome and the distinguishing condition, so an agent can separate it from that tool without reading schemas.

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 timing cue ('After the user reports what happened') and an explicit alternative with its selection condition ('Use report_action_outcome for a durable report tied to the current packet revision and route'). It also draws the boundary that this does not verify an action, which further disambiguates usage.

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