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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely new behavioral context: results are paginated one page per call and totals across pages require summarize.all_pages, which prevents a common under-fetching mistake.

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 with zero filler: identity, endpoint provenance, and the pagination caveat. The most actionable constraint (one page per call) is front-loaded before the alternate-totals advice.

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?

An output schema exists and annotations cover the safety profile, so the description needn't explain return values or risk. For a 19-parameter tool with a nested summarize object, the description adequately covers the main behavioral pitfall (pagination), though it leaves filter/expand semantics entirely to the schema.

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 high (84%) across 19 parameters, so the schema itself documents the filter, sort, fields, and summarize properties in detail. The description only adds a note about summarize.all_pages and says nothing about the many filter or expand parameters, so it neither compensates for nor exceeds the schema baseline.

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 ("Retrieve a list of customers") and anchors it to the underlying Fortnox endpoint GET /3/customers, so an agent knows exactly which resource is being read. It does not explicitly contrast with the singular get_customer sibling, leaving that inference to the name alone.

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?

"One page per call; use summarize.all_pages for totals over every page" gives concrete operational guidance on when the plain call is insufficient and what to use instead. It stops short of stating when to prefer list_customers over get_customer or the summarization/aggregation siblings.

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