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

Annotations already declare readOnly=true, destructive=false, openWorld=true, so the safety profile is covered. The description adds useful behavior beyond that: default/max page size and the pagination formula, plus the data model field naming convention.

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 core action and then mechanics; four sentences with little waste. Slightly dense but every part carries information an agent needs.

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?

No output schema, but the description names example return fields and paging semantics, and the schema fully documents filter/order/fields. Complete enough to call correctly, with only minor gaps in describing the response envelope.

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% (baseline 3), and the description adds value beyond it: concrete field examples (costCenterId, name, code) and the explicit offset = offset + limit paging rule for the offset/limit params.

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 (List) and resource (cost centers) with a Spanish alias for disambiguation, and the endpoint POST /purchases/costcenters/list makes the operation unambiguous against the many get_* and list_* siblings.

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?

Explains when/how to page: 'When a page is full, ask for the next one with offset = offset + limit.' Clear usage context, though it does not explicitly name alternatives for filtered single-record lookups versus list_* siblings.

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