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

Annotations already say readOnly/non-destructive, but the description adds the crucial mechanism: a form opens, the user picks the PDF/photo, reviews the data, sets the consent checkbox for lawyer referral, and submits themselves — the tool transmits nothing. It also notes fields can be prefilled (e.g. the deadline). This is exactly the behavioral context an agent needs and cannot infer from structured fields.

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 trigger condition, then behavior, then exclusions — good ordering. The parenthetical case-type and English-synonym enumerations are long but each aids retrieval matching; the only cost is density, not wasted sentences.

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?

No output schema is needed since the tool returns a UI form rather than data, and the description covers what the form does, who submits it, what consent is required, and what the tool explicitly does not do. Everything required to invoke it correctly is present.

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 each parameter is already documented, including the "falls sie sie genannt hat" optionality. The description adds only a light hint that fields may be prefilled, e.g. the Frist from the letter, which is marginal beyond the schema and does not explain formats such as JJJJ-MM-TT.

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 concrete action on a concrete resource: it opens the in-chat form "Abmahnung einsenden" for a cease-and-desist/demand letter. It explicitly distinguishes itself from the sending sibling by declaring "dieses Werkzeug sendet nichts", so an agent can separate it from abmahnung_absenden.

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 an explicit trigger (person received a Abmahnung/Unterlassungserklärung/Zahlungsaufforderung) and an explicit, unusually thorough exclusion list — general legal questions, payment reminders/Inkasso, employer or landlord warnings, criminal matters, and any request for the app itself to assess the case. Alternatives are named in prose (specialist lawyer, Abmahnexperte.de, free initial assessment).

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