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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered; the description adds real context beyond that — results are ordered newest first and an empty array carries a specific meaning (no customers registered). Pagination and the dual response shapes are left to the schema, which is fine.

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?

Two sentences, no filler; the primary purpose and the ordering guarantee come first, and the empty-state recovery path follows. Every clause earns its place.

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 zero-required-param, read-only list tool with full schema coverage and no output schema, the description covers what the call is for, what ordering to expect, and what to do when it returns nothing. The only gap is not steering agents to myinvois_customer_search when they actually want filtering.

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 description coverage is 100% and the schema already explains limit range, cursor opacity, and the legacy bare-array vs {items, next_cursor, limit} behavior. The description adds no parameter-level information, so baseline 3 applies.

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?

"List registered buyers, newest first" gives a specific verb, resource and ordering, and ties the output to a concrete downstream need (customer_id for myinvois_invoice_generate). It does not distinguish itself from the sibling myinvois_customer_search, so an agent still has to infer whether listing or searching is right.

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?

Purpose-driven usage is explicit: call this to obtain a customer_id for invoice generation, and the empty-list case routes to myinvois_customer_create or an inline {name, tin}. No exclusion against myinvois_customer_search or myinvois_customer_read is stated, which keeps it 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.