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

Annotations only declare readOnlyHint=true, so the description carries real weight and delivers: it discloses the response envelope ({ charges }), pagination mechanics (next_cursor / previous_cursor), default and max page size, and a non-obvious API constraint that would otherwise cause silent failures on cursor requests. That is meaningful behavioral context beyond the annotation.

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-loaded with purpose, then return shape, then the pagination constraint, then the REST endpoint for traceability. The parenthetical filter enumeration partially duplicates the schema, but everything else earns its place and the critical warning is not buried.

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 15 parameters, no required fields, and no output schema, the description supplies exactly what is missing elsewhere: the response envelope, paging loop mechanics, and the cursor exclusivity rule. An agent has enough to call this correctly and paginate safely.

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% and the schema itself already documents limit bounds, the cursor caveat, enum values, and every filter. The description restates the filter list and the limit default/max rather than adding format or precedence detail, so this lands at the baseline for high coverage.

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?

States a specific verb and resource ("List charges") and immediately enumerates the filter dimensions and sorting capability, which cleanly separates it from the single-resource sibling recharge_get_charge. An agent can distinguish it from recharge_list_orders / recharge_list_customers without opening a schema.

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 clear operational context: optional filters, cursor-based paging, and the hard constraint that cursor requests accept ONLY `limit`. It does not explicitly say when to prefer this over recharge_get_charge or sibling list tools, but for a list endpoint on a distinct resource that inference is essentially trivial.

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