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

The annotations already declare readOnlyHint=false and idempotentHint=true, but the description adds meaningful context: the write only lands as a DRAFT awaiting human approval and never touches the accounting ledger, which reconciles the apparent tension of a non-read-only tool. It also sharpens idempotency with a scope qualifier ('per open finding') that the bare annotation does not convey. It stops short of explaining what happens to existing drafts or what the call returns.

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 short sentences, front-loaded with the action, followed by the safety guarantee and the idempotency note. Every sentence carries distinct information and none restates the tool name.

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 one-parameter tool with rich annotations, the safety and idempotency picture is complete, but two gaps remain: 'anomalies' is never defined, and with no output schema the description says nothing about what is returned (count of proposals, their identifiers, or an empty result). An agent knows it is safe to call but not what to expect back.

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?

There is a single parameter whose schema description is fully covered ('Id from list_connections'), so the schema does the work. The prose adds nothing about connection_id or how scan scope is determined by it, which is the expected baseline for a one-param tool with 100% coverage.

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 pairs a specific verb with a specific resource: it scans for anomalies and files them as DRAFT proposals in JaKonto. That clearly separates it from the read-only sibling list_proposals, though the description never names that sibling, so the agent must infer the pairing.

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?

Usage is implied rather than stated: 'for a human to approve' suggests this is the initiation step of a proposal workflow, and 'Never writes to the accounting system' reassures about scope. However, there is no explicit when-to-use or when-not-to-use guidance, and no indication of prerequisites such as whether connections must first be verified via list_connections.

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