withdraws_init

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

Annotations already declare destructive=true, idempotent=false and openWorld=true, so the safety profile is covered structurally. The description adds nothing beyond that: it does not say funds are actually moved, whether the withdrawal executes immediately or awaits confirmation, what permission/balance conditions apply, or what is returned (e.g. a withdrawal id).

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 terse fragments with no structure; the raw "POST /withdraws" line consumes space without helping an agent decide or invoke. It is short, but the brevity is under-specification rather than efficiency.

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 destructive, non-idempotent financial mutation with a nested required body and no output schema, the description omits nearly everything an agent needs: the effect on balance, error/insufficient-funds behavior, and the shape of the response. Only the annotations supply behavioral context.

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 0% and the single top-level parameter is a nested object with four fields (amount, wallet, fileIds, methodId), only one of which has any schema description. The description provides zero field-level meaning — it doesn't clarify amount semantics/limits, when wallet is required, or what fileIds are for — leaving most of the payload undocumented.

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?

"Init new withdraw" essentially restates the tool name with an abbreviated verb, and "POST /withdraws" is endpoint trivia rather than a description of purpose. It never explains what a withdrawal actually does (moves funds from balance to a wallet/method) or how it differs from the withdraws_get_* siblings beyond the name prefix.

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?

There is no when-to-use guidance, no prerequisites (e.g. that a method must be fetched first), and no mention of alternatives or conditions under which a withdrawal should not be initiated. The only hint toward a prerequisite lives in the schema's methodId description, not in the tool description.

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