manage_funds

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

The description goes well beyond the annotations by disclosing that add is only a top-up *request* rather than instant credit, and that transfer/withdraw execute money movement in this one call with no confirm_hash. This is exactly the kind of non-obvious behavioral context (latency, irreversibility, missing confirmation step) that annotations cannot express. It aligns with destructiveHint=true and readOnlyHint=false, with no contradiction.

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 extremely compact—five short lines with no filler—and front-loads the domain, then the action taxonomy, then the danger warning. The fragmentary style ('Funds.', 'Danger gate.') is somewhat cryptic, but every token earns its place and the most critical warnings are placed at the end for emphasis.

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 medium-complexity tool with an output schema present and annotations covering the read-only/destructive profile, the action taxonomy and danger tiers are well covered. The gaps are the ambiguous referent of 'Danger gate' (whether confirm=true is the gate or the tool itself requires gating) and the unexplained parameters. Adequate for safe invocation of the core actions, but with clear room for clarification.

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%, so the description carries the burden. It does compensate for the safety-critical parameters: amount is defined as a Gram (or EUR) string, and the confirm/no-confirm_hash behavior is flagged. However, query, account_id, and additional_comment receive no explanation, and the exact role of the confirm boolean is left ambiguous. Meaningful additions, but roughly half the parameters remain unexplained.

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 description identifies the resource (funds) and enumerates five distinct actions (list/search/add/transfer/withdraw) with differentiated semantics, so an agent can tell what the tool does. It clearly belongs to the funds domain and is distinguishable from the ad/account siblings. The opening 'Funds.' is telegraphic but not a tautology, since it is backed by operational detail.

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?

The description explicitly tiers actions by safety and behavior: list/search are lookups 'not gated', add is a deferred top-up request, and transfer/withdraw move money immediately with a 'Danger gate'. This gives an agent a usable decision rule for choosing among actions. It does not reference sibling alternatives, but no sibling handles funds, so within-tool action routing is the relevant guidance.

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