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

The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description reinforces this with 'This reads Fortnox; it never sends the change again,' but adds little beyond that and does not explain what information the resolution 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?

The definition is two short sentences with the key condition and non-mutating behavior front-loaded. There is no filler or repetition.

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?

The description is very sparse for a tool with two parameters, a nested path_params object, and no output schema. Annotations cover the safety profile, but the description does not compensate for the undocumented parameters or explain what resolution result the caller should expect.

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 description does not mention the required idempotency_key or the path_params object. For a resolution tool, the idempotency key is central to identifying the ambiguous write, so the missing parameter context is a significant gap.

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 states a specific purpose: finding out what happened to a write that ended as ambiguous. It is clearly distinct from mutation siblings like execute_fortnox_write because it says it reads Fortnox and never resends the change, though it does not explicitly name list_fortnox_writes or other alternatives.

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?

It gives a clear triggering condition: use it for a write whose outcome is ambiguous. The phrase 'never sends the change again' also implicitly steers the agent away from retrying the original write, but no sibling tools are named as alternatives.

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