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

Goes well past the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true): it discloses the DRAFT default, that a DRAFT group blocks its campaigns from being set to PAUSED/ACTIVE, exact UTC day boundaries for start/end, the start_in_past error, and a readback verification contract (verified, not_applied, readback_failed) with retry guidance. That is exactly the mutation-behavior context annotations cannot convey.

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?

Front-loaded with the action and default status, then conditions, then return/verification semantics — a sensible ordering. It is dense with stacked parentheticals about date handling, so a reader must parse carefully, but no sentence is filler given the 8 undocumented parameters.

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?

An output schema exists, yet the description still summarizes the key return fields (campaign_group_id, status, verified) and the failure semantics, and it covers almost every parameter's edge case. The only meaningful holes are currency and validate_only, which an agent may need to know exist before calling.

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 carries the burden and mostly succeeds: it explains status defaulting to DRAFT, total_budget as an optional upper bound that forces end_date, start_date/end_date inclusive UTC semantics with a concrete format, and workspace as a slug needed only when multiple workspaces exist. Only currency (default EUR) and validate_only are left completely unexplained, so it falls short of full 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?

States a specific verb and resource ('Neue LinkedIn-Kampagnengruppe anlegen') and immediately distinguishes this creation tool from the campaign-level and update tools, naming linkedin_update_campaign_group as the activation path. An agent can tell it apart from linkedin_create_campaign and linkedin_list_campaign_groups without opening any schema.

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?

Gives concrete use conditions: group is created as DRAFT by default, activation must go through linkedin_update_campaign_group, and the tool should not be re-run when verified=null due to readback_failed. It also states the total_budget → end_date dependency and the start-in-the-past failure mode, though it never explicitly says when not to use it (e.g. vs. linkedin_create_campaign for child campaigns).

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