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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=true, so the description does not need to restate that it writes. It does add real value beyond them: the number is assigned by Lexware, uniqueness must be guarded by pre-checking list_contacts, and per-contact limits (one billing, one shipping, one email, one phone). It omits auth/permission needs and duplicate-handling behavior, so not a 5.

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?

Five short sentences, front-loaded with the "WRITE:" signal and ending with the endpoint. Every clause carries a distinct constraint (identity path, cardinality limits, duplicate check, HTTP target); nothing is redundant with the title.

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 20-parameter, mutation, non-idempotent tool with no output schema and zero required fields in the schema, the description covers the essentials an agent needs: identity requirements, cardinality caps, and the duplicate-avoidance step. It does not cover role defaults, the meaning of the xrechnung/contact-person field clusters, or what the response returns, leaving some gaps.

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 70%, so the baseline is 3, but the description adds cross-field semantics the schema never states: company_name and person_last_name are mutually alternative identity paths, and email/phone/address are singular. It leaves the roles enum (customer/vendor default), note, tax_number, and the contact_person_*/xrechnung_* fields unexplained.

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?

Opens with a specific verb+resource ("WRITE: creates a new customer and/or vendor in Lexware Office") and adds distinguishing scope: the number is server-assigned, and address/email/phone cardinality is capped. This clearly separates it from the read-side siblings lexware_get_contact, lexware_list_contacts, and the create_draft_* tools that operate on other resources.

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 concrete selection rules ("company_name for a company OR person_last_name for a private person") and a prerequisite workflow ("Check lexware_list_contacts first to avoid duplicates"), naming a sibling tool explicitly. There is no explicit when-not-to-use or guidance on choosing between customer and vendor roles, 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.