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

With no annotations, the description carries the full burden and succeeds. It discloses a side effect (sends email to operator), duplicate-detection behavior (returns existing LNURL instead of creating a duplicate), and the 30-day expiration of refund links. This goes well beyond basic expectations.

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 dense but every sentence adds value. It front-loads the core purpose, then provides critical exceptions and warnings without redundancy. The structure is logical and scannable.

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 tool with 4 parameters, no output schema, and no annotations, the description covers the use case, exclusions, side effects, and expiry thoroughly. However, it doesn't specify what the agent should expect in the successful response for the normal manual ticket creation (e.g., a ticket ID), which is a minor gap given the absence of an 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 description coverage is 100%, so parameters are already fully documented. The description does not add additional parameter-specific meaning; it focuses on behavioral context. 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?

The description clearly states the tool's purpose: 'Open a MANUAL 48-hour refund review ticket for a service that FAILED (error, timeout, wrong output).' It also distinguishes itself from automatic refunds by explicitly naming the sibling services (ai_call, voice_bridge) and instructing not to use this tool for those cases.

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?

Provides explicit when-to-use ('for a service that FAILED') and when-not-to-use guidance ('DO NOT call this for unused-minute refunds on metered services'). It also explains the fallback behavior for metered payments with pending LNURL refunds and includes the 30-day claim window, which is critical for agent decision-making.

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