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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, so the safety profile is covered. The description adds a genuinely non-obvious constraint beyond structured data: the schema lists zero required parameters, but the tool actually requires at least one of first_name/last_name/company_name. It does not say what happens on a rejected or duplicate create.

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?

Three short sentences, front-loaded with the operation type and immediately followed by the actionable constraint and the duplicate check. The trailing 'POST /customers' adds little for an agent but costs almost nothing.

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 with no output schema, the description covers the essential precondition and the duplicate guard, but omits what the response contains (e.g., the newly created customer id needed for follow-up calls) and how most optional fields behave.

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?

With 20 parameters and only 25% schema description coverage, the description must carry meaning about the fields but mentions only the name trio. Address, loyalty, consent, and customer_code parameters are left entirely to bare schema property names, so the coverage gap is not compensated.

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 ('create a new customer') and prefixes it with 'WRITE', making the operation type unambiguous. It is distinguishable from update_customer and get_customer, though it never explicitly names update_customer as the mutation alternative.

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?

Explicitly directs the agent to run search_customers first to avoid duplicates, which is a real alternative-tool routing rule. It also gives the precondition that at least a first name, last name, or company name must be supplied, though it does not cover failure behavior or when-not-to-use cases.

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