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

The description discloses a concrete side effect beyond the annotations: 'Die gefundenen Logos werden als Design-Assets im Konto gespeichert' (found logos are stored as design assets in the account), which specifies what the write actually does given readOnlyHint=false. It also reveals the behavioral trait that the result is only a proposal, not a committed brand, adding commit semantics that the annotations cannot express. No contradiction with 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 description is front-loaded with the core function in the first sentence and progresses logically to side effects then workflow. However, the full German text is duplicated verbatim in English, roughly doubling length, and the trailing instruction 'Suche technisch nach brand_import_from_website / Search technically for brand_import_from_website' is a search-index artifact that adds no value to an agent deciding whether to call the tool.

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?

With no output schema present, the description compensates by explaining what the result is (a proposal for customer review) and enumerating its contents (colours, typeface, logos, imprint data). The required follow-up step and the brandingOwnershipConfirmed flag are also covered, giving the agent the full lifecycle. The main gap is the absence of detailed response-shape expectations, but the description is adequate for a moderate three-parameter tool.

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 websiteUrl (with example), maxLogoCandidates (with default and range), and reasoning (audit log rationale). The description reinforces the logo-candidate concept by listing 'Logo-Kandidaten' as an output, but it adds no parameter-level meaning beyond what the schema provides. Baseline 3 is appropriate when the schema carries the full burden.

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: 'Liest eine oeffentliche Firmenwebsite aus und schlaegt daraus ein Briefkopf-Design vor' (reads a public website and proposes a letterhead design), then enumerates concrete outputs (brand colours, house typeface mapping, logo candidates, imprint data). The description explicitly distinguishes this tool from the adoption step by naming brand_kit_save as the separate follow-up, removing ambiguity with sibling tools.

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 two-phase workflow is explicit: this tool produces a proposal for customer review, and the brand is only adopted by a subsequent brand_kit_save call carrying brandingOwnershipConfirmed. This tells the agent when this tool ends its job and where routing continues. It falls short of explicitly stating when NOT to use it or contrasting it with alternatives like letter_design_list_presets, but for a specialized import tool the workflow guidance is strong.

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