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

Annotations already declare readOnlyHint=false and openWorldHint=true, but the description makes the real-world consequence concrete: the enquiry reaches an actual company, so mistakes are externally visible. It also discloses the anti-fabrication constraint on the email. It does not cover duplicate-send behavior or failure modes (e.g. invalid slug), which would complete the picture.

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 critical warning ('only when the user explicitly asks') is front-loaded in the first clause. The main waste is the full German-to-English duplication, which roughly doubles length for no additional information, though it is defensible for a bilingual tool surface.

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 five parameters, no output schema, and annotations that already flag the operation as non-readonly and open-world, the description supplies the missing safety context an agent needs before calling it. It stops short of describing what a successful or failed send returns, which is the only notable gap given there is no output schema.

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 100%, so the baseline is 3, but the description adds genuinely new semantics: the slug must originate from a search result rather than a company name, and the email must be supplied by the user. These are value/derivation constraints the schema's 'Der Slug der Firma' does not convey.

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 ('Schickt eine Anfrage an ein Unternehmen, im Auftrag des Nutzers') so the agent immediately knows this performs an outbound send. Siblings firma_abrufen and firmen_suchen are read operations and the difference is inferable, though no sibling is named explicitly.

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 precondition ('Nur benutzen, wenn der Nutzer das ausdrücklich will'), a hard data-source rule for the email ('muss vom Nutzer kommen, nicht erfunden sein'), and routes the slug requirement to a prior search ('der Slug aus einem Suchtreffer, nicht der Firmenname'). This effectively encodes the firmen_suchen -> anfrage_senden workflow without leaving it to inference.

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