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

Annotations only declare the mutation/safety profile; the description adds the meaningful behavior that the call is gated on external approval state and is a no-op when unapproved, which is not derivable from the annotations. It stops short of saying what happens on a repeat call after success or how failures surface, so not a 5.

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?

Two sentences, with the gating condition front-loaded before the action description. Dense but every clause carries information; the parenthetical action list is slightly long but justifies the tool's breadth.

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?

There is no output schema, and the description never says what a successful run returns (status, created resource id, price charged) despite the action being heterogeneous. The precondition side is complete, but the result side is left to inference.

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 both parameters are already documented, including the BCP-47 language semantics. The description only reinforces that approvalId comes from the approval link, adding little beyond the schema; baseline 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?

States a specific verb chain ('checks the approval with Ania and runs the action') plus the concrete resource classes it can execute (avatar creation, adjustment, wake-word training, marketplace purchase). This clearly separates it from siblings like play_action or approve_image, which do not take an approvalId.

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 an explicit precondition ('Only after an Ania tool returned an approval link (approvalId) and the user says they clicked "Approve spend"') and an explicit negative case ('If it is not approved yet, nothing happens'). An agent knows both when to call and when not to.

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