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

Annotations already declare readOnly=false, idempotent=false, destructive=false and openWorld=true. The description goes well beyond that by disclosing the duplicate-name failure mode ('Merit answers with an error'), the absence of downstream side effects ('Nothing is invoiced, sent or paid'), and the return value, since there is no output schema.

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 WRITE marker and the highest-value fact (uniqueness/error), then the no-side-effects note, then the conditional rules. Every sentence carries weight; the Estonia sentence's phrasing ('city is required in Estonia for a non-EE country') is slightly dense but not wasteful.

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 17-parameter mutation tool with no output schema, it covers the critical gaps: return value, duplicate handling, and country-specific validation. It omits auth/company-scoping prerequisites and the exact error payload shape, which are the remaining unknowns for correct invocation.

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 contributes cross-field conditional logic the schema cannot express: not_td_customer must be true for Estonian private persons and foreign companies, and city becomes required for non-EE countries in Estonia. It does not explain the Poland-specific variants beyond what the schema already states.

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 an explicit WRITE marker and a specific verb+resource+cardinality ('creates ONE new customer record'), which immediately separates it from merit_list_customers and the vendor-side siblings. The uniqueness constraint and POST endpoint name add further precision about what is actually created.

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 clear context for use: uniqueness requirement, the fact that an existing customer is never overwritten, and Estonia-specific conditions for not_td_customer and city. It stops short of naming an alternative (e.g. merit_list_customers to check for duplicates first), so the agent must infer the lookup-before-create workflow.

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