manage_funds

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

The description adds useful behavioral context beyond the annotations: currency is determined by the cabinet (Gram or EUR), amounts are strings, and add is characterized as a request. It does not explain side effects of withdraw/transfer, potential approval flows, or how openWorldHint/destructiveHint apply per action, leaving part of the burden unmet.

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 compact and front-loads the key currency rule before the action list. The line-broken action list is easy to scan, though the opening 'Funds.' is a bit cryptic and could be replaced with a complete sentence without bloating the text.

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 five-parameter, multi-action dispatcher with destructive and non-idempotent operations, the description is too thin: it does not address action-specific parameter use, prerequisites, or operation outcomes. The output schema may cover returns, but an agent cannot reliably construct a correct call without knowing which fields matter for each action.

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?

With 0% schema coverage, the description needed to define all parameters, but it only glosses the action enum and the amount-as-string rule. query, account_id, and additional_comment are left undefined, and there is no mapping of which parameters are required per action.

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 action list (add/transfer/withdraw/search/list) makes the tool's function concrete and separates it from account/listing siblings. However, the opening 'Funds.' is a noun fragment rather than a verb-led statement, so the overall purpose relies partly on the tool name.

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?

Action annotations ('top-up request', 'find a cabinet', 'linked cabinets') imply when each operation is appropriate. There is no explicit guidance on choosing manage_funds over sibling tools like list_accounts or get_account, and no when-not-to-use conditions.

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