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

Annotations already declare the mutation/idempotency profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), so the bar is lower. The description still adds real value beyond them: the call is free ('Kostet nichts'), it returns at most three questions plus a next_step directive, and it specifies that the response must be rephrased for the user rather than shown as JSON. It does not explain what state the created project leaves behind or how the ORG_AMBIGUOUS error should be handled beyond the schema note.

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 is front-loaded in the first sentence and the operational directives come last, which is the right order. The bilingual duplication (full German text plus an English restatement) is partly redundant, though it does serve non-German agents; nothing else is padding.

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?

There is no output schema, but the description compensates by describing the return shape (up to three next_questions with proposed values, plus next_step) and the cost profile. With five parameters at full schema coverage and clear mutation annotations, an agent has what it needs; only the post-call workflow (what to do after the questions are answered) is left implicit.

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 100%, so the schema already documents brief, kunde, title, organization and client_request_id thoroughly. The description only restates the brief parameter ('Nimmt den Wunsch der Person in ihren eigenen Worten (brief)') and adds no format or constraint detail beyond what the schema provides. Baseline 3 applies.

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 ('legt ein Leadprojekt an' / 'starts a lead project from the user's own words') and positions itself as the entry point of the workflow ('Der Anfang jeder Lead-Liste'), which separates it from planning/confirmation siblings like plan_pipeline_run or confirm_pipeline_run. The English gloss removes any ambiguity for a non-German reader.

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?

Clear about the context of use: it takes the user's request in their own words and returns follow-up questions, and it instructs the agent to ask at most three, offer the proposed default, and follow next_step. There are no explicit when-not-to-use conditions or named alternatives (e.g. when to prefer draft_pipeline instead), 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.