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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so safety is covered. The description adds genuinely useful pagination behavior ('one page per call') and the endpoint reference, but says nothing about default page size, total-count reporting, or what an empty/unauthorized response looks like.

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 waste: identity first, API grounding second, pagination/aggregation caveat third. The most decision-relevant constraint (one page per call) is front-loaded effectively.

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's main burden is the pagination/aggregation ambiguity, which it addresses. Minor residual gap: it doesn't explain what 'expand' or 'fields' projections do to the returned rows, which matters for a sparse-by-default list tool.

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?

At 63% schema description coverage with 8 parameters including a nested summarize object, the description only clarifies one sub-parameter (all_pages); page, limit, offset, expand, fields, sortby and sortorder are left entirely to the schema. The all_pages hint is valuable but does not compensate for the remaining undocumented surface.

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+resource ('Retrieve a list of cost centers') and ties it to the underlying Fortnox endpoint GET /3/costcenters, so the agent knows exactly what data comes back. It does not contrast itself with similar analytics siblings like get_result_by_cost_center_or_project, so differentiation is only partly achieved.

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' plus the pointer to summarize.all_pages for totals gives an implied usage pattern (paginate for raw rows, aggregate for totals). However, there is no explicit when-to-use vs when-not, and no mention of when list_projects or get_result_by_cost_center_or_project should be preferred.

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