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

Annotations flag this as destructive/open-world, but the description adds the crucial real-world semantics: recurring automatic charges to a saved card, the prerequisite that a card exists, and the consent requirement. That is meaningful context beyond the annotations, though it doesn't cover failure modes (e.g., charge declined) or how to inspect current settings.

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?

Three tight sentences: the core action first, then the behavior, then prerequisites and the confirm asymmetry. No wasted wording.

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 mutation with no output schema, the description covers what's needed to invoke it correctly — prerequisites, consent, and the enable/disable asymmetry. It stops short of describing the result (e.g., whether a confirmation or current state is returned), but nothing essential is missing.

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%, so the schema already documents all four parameters; the description still adds value by tying amount_usd and threshold_usd together in a conditional relationship and clarifying that confirm is only for enabling.

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?

Uses a specific verb+resource (turn wallet auto-recharge on/off) and immediately explains the mechanism (charges saved card amount_usd when balance falls below threshold_usd). It is clearly distinguishable from spur_top_up_wallet, though it mentions that sibling only as a prerequisite rather than as an explicit alternative.

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 concrete conditions: requires a saved card, requires user approval of amount and threshold (confirm=true) when enabling, and no approval when disabling. It does not explicitly say when to prefer one-off spur_top_up_wallet over auto-recharge, which keeps it 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.