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

Goes well beyond the destructive/openWorld annotations: it discloses that the tool reads the campaign back before/after for verification, that validate_only performs only a local check without writing, that LinkedIn rejects mismatched strategy/objective pairs, and that amount=0 results in no delivery. For a destructive mutation these are exactly the operational facts an agent needs.

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?

Purpose and read-back behaviour are front-loaded, then parameters are grouped into scannable bullets grouped by strategy family. It is dense and long, but nearly every line carries operative information; only slight tightening of the strategy enumeration would be possible.

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 six-parameter destructive mutation with an output schema present, the description covers purpose, per-strategy parameter rules, server-side validation risk, dry-run path, and workspace scoping. Nothing an agent needs before invoking it is missing.

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 description coverage the description must carry the full burden, and it does: optimization_target values are enumerated by category (manual, max delivery, target cost, cost cap), amount is defined per cost_type (CPC vs CPM vs CPV), cost_type is documented as optional with fallback to the existing billing mode, and validate_only/workspace are explained.

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 opening clause names a specific verb and resource ('Gebotsstrategie und Gebotsbetrag einer LinkedIn-Kampagne ändern') and adds the read-back/verify behaviour. Within a sibling set that contains separate budget, name, status, schedule and targeting updaters, 'Gebotsbetrag' unambiguously places this tool on bid configuration rather than budget.

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 explicit conditional guidance on which optimization_target applies to which campaign objective and when amount is required versus ignored, plus validate_only as a dry-run path. It does not name a competing sibling tool to route away from, so it stops short of a 5.

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