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

Annotations only supply openWorldHint=false, so the description carries nearly the full burden and does well: it discloses that the call is free to the user, that a human at Fizzl reads every report, that nothing is executed or changed automatically, and that the wallet auto-attaches the caller's own receipt. It still omits what the call returns (a confirmation or id) and any rate limits, so it is strong but not complete.

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?

The description is front-loaded with the purpose, then the payment branch, then the privacy warning — a sensible order. A few phrases are padded ('Free, and it costs your user nothing' restates the same point twice), which keeps it from a 5, but nothing is extraneous to correct invocation.

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 5-parameter tool with a nested object and no output schema, the description covers purpose, eligibility, privacy, and payment routing thoroughly. The remaining gap is the absence of any statement about what a successful submission returns or how the agent should report the outcome to the user.

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 100%, which sets a baseline of 3, and the description earns an extra point by explaining the conditional use of the nested payment object: attach tx (the settlement transaction from the pay answer) plus network, or a receipt_id, specifically when a paid call went wrong. It also adds the safety constraint that secrets and personal data must never be placed in the message or contact fields.

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 opens with a specific verb and target: 'Tell Fizzl what is missing or broken in this wallet', then enumerates the qualifying categories (missing network/coin, unfindable service, blocking limit or step, bug). That framing makes it unmistakable against siblings like find_services, check_text, or pay_x402, which are lookup/action tools rather than a report channel.

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 concrete triggers for when to use it, including the payment-specific branch ('If it is about a payment that went wrong... add payment with its tx... or receipt'). What is missing is an explicit exclusion or named alternative — e.g. 'use find_services first; only report if it fails' — so the agent must infer that from the categories.

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