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

With readOnlyHint=true, the description still adds valuable behavioral context: role-dependent filtering, the fields included in each entry, and ordering behavior for undelivered_only. It does not mention auth or rate limits, but annotations already cover the read-only nature.

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 concise but packs in multiple pieces of information: role behavior, return field details, and undelivered_only semantics. It is well-structured and front-loaded, though slightly longer than strictly necessary.

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?

Despite having no output schema, the description fully covers return value contents and behavioral nuances. All parameters are adequately described either in the schema or the description, and the read-only annotation combined with this context leaves no significant gaps.

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%, and the description adds meaning beyond the schema by explaining role outcomes ('what you were paid' vs 'what you paid other sellers') and clarifying undelivered_only as 'everything you owe somebody, oldest first'. The limit and service_id params are already self-described in the schema.

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 lists payments on your services, with role-specific behavior for seller (what you were paid) and buyer (what you paid). This is a specific verb+resource and distinguishes itself from siblings like charge_create or charge_refund.

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?

The description explains when to use each role and introduces undelivered_only for obtaining your delivery queue. It gives practical usage context but does not explicitly name alternative tools for exclusions, so it falls short of a 5.

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