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

Annotations already declare non-readonly, non-idempotent, non-destructive behavior, and the description goes well beyond them: a rule violation aborts with HTTP 400 and returns per-field errors while saving NOTHING, a 'sent' answer becomes locked and resubmitting creates a new answer, and no mail goes out without an 'action' button. These are precisely the behavioral traits an agent needs for a mutation tool.

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 long but front-loaded with the core action and every sentence carries operational information (button semantics, validation contract, locking). Some clauses are dense and could be trimmed, but there is no filler or repetition.

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?

For a complex mutation tool with nested objects and no output schema, the description covers the full lifecycle: input sources, save-vs-send, action/button routing, validation failure format, and post-send immutability. An agent has everything needed to call it correctly and to interpret failures.

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 coverage is already 100%, so the baseline is 3, but the description adds real meaning on top: the subform representation (a field receiving a list of row objects, with a concrete JSON example and where the row keys come from) and the nuance that recipients/subject are deliberately not request-settable. It clarifies the interplay of status and action beyond the schema text.

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 opening states a specific verb+resource ('Formular-Antwort SPEICHERN oder ABSENDEN') and immediately distinguishes the create-vs-update path ('OHNE answer_udid wird eine NEUE Antwort angelegt'). It also maps each input to its source tool (form_udid from list_formdefs, answer_udid from prepare_form_answer), so an agent can place it in the workflow without opening the 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?

It states the prerequisites and the alternatives clearly: save with 'draft', commit with 'sent', and a new answer is created when no answer_udid is supplied. The validation-testing use case ('Genau damit testest du ein Formular fachlich durch') gives explicit when-to-use context, though it does not name conditions under which another tool should be preferred.

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