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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the description carries extra burden. It adds crucial behavioral context beyond annotations: the permission requirement (approval:self_approve), that card view and cardNonce are only preview evidence, and that missing permission routes to the browser. It still omits what happens to the approval record on approve vs reject and whether the effect is reversible.

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 duplicated in German and English, roughly doubling its length with no added information. Most sentences earn their place, but the bilingual repetition wastes tokens and is not front-loaded; the key permission condition is buried after the generic opening.

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 mutation tool with no output schema and 0% schema coverage, the description covers the critical gating condition and fallback, but leaves the semantics of decision, reasoning, and approvalId unexplained, and does not describe the return behavior of a successful call. It is adequate but not complete.

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 must compensate. It explains cardNonce only as 'preview evidence', which is useful, but adds no meaning for approvalId, decision, or reasoning beyond what the schema types/enums already imply. Baseline is 3 for low coverage; the cardNonce hint is a small addition but the other three parameters remain undescribed.

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 verb and resource: 'App-internes Entscheidungs-Tool' / 'Internal app decision tool' that approves or rejects based on an OAuth permission. This is clearly distinguished from siblings like approval_decide and template_decide_app by the 'app-internal' scope and the OAuth requirement. However, it never explicitly names the artifact being decided on (approval) or the possible decisions, relying on the schema for that.

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 condition for when a call 'may approve': when the verified OAuth connection carries approval:self_approve. It also explains fallback behavior when permission is absent (the card leads to the signed-in browser). It does not explicitly contrast this with approval_decide or template_decide_app, but the app-internal framing and permission gating imply the separation.

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