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

Beyond the annotations (readOnlyHint=false), the description discloses a genuine side effect: the call triggers a real e-mail and should only be used for serious, genuine requests. It also sets expectations that no private contact data is returned, which is not inferable from the schema or annotations.

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 English text is front-loaded and logically structured: action, requirements, return value, prerequisites, optional parameters, flow, warnings, and terms. However, the full German translation roughly doubles the length without adding new functional information for an agent reading the English description.

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 covers side effects, the return value (request_id), prerequisites, the canonical flow, and the absence of private-data returns, all of which are essential because there is no output schema. It also includes operational guardrails such as no bulk requests, no test calls, and applicable terms of use.

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 compensates by naming all five parameters: name and email must belong to the requesting brand, creator_public_ids must come from a previous search, and message and search_query are optional free-text context for UGC VZ. It does not repeat schema constraints but adds the missing semantic layer.

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 names a precise verb and resource: it 'triggers a deliberate brand request' and explains the real-world consequence (UGC VZ forwards creator contact details by e-mail). It also differentiates itself from sibling search/get tools by stating it returns only a request_id and no creator or private contact data.

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?

The description gives explicit preconditions ('Creators must have been found via search_creators or get_creator before this call'), a canonical flow (search_creators -> get_creator -> request_outreach -> get_outreach_status), and clear exclusions ('No bulk requests, no test calls'). This leaves little ambiguity about when the tool should and should not be used.

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