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

Annotations already declare readOnly, idempotent, and non-destructive, so the description correctly focuses elsewhere. It adds genuinely non-obvious behavior: results are paged one page per call, and totals across all pages require summarize.all_pages — a real trap an agent would otherwise fall into. It stops short of stating the default page size or total record ceiling.

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 compact sentences, with the core action front-loaded before the endpoint citation and the pagination caveat. The API docs URL is defensible for reference and nothing is padded.

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?

Return shape is covered by the output schema, so omission there is fine, and the pagination caveat is the most important missing-context item. But for an 11-parameter, nested-object listing tool with zero required params, key semantics (filtering, page sizing, field projection) and the sibling boundary remain unaddressed.

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 11 parameters and only 55% schema description coverage, the description should carry more weight. It explains only the nested summarize.all_pages flag; sru, page, limit, offset, lastmodified, and financialyear (page-size defaults, date formats, sorting interaction with paging) are left entirely to the thin schema.

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 ("List all accounts") and anchors it to the concrete Fortnox endpoint GET /3/accounts. It does not differentiate from close siblings such as get_chart_of_accounts or get_account_ledger, which an agent could plausibly confuse with an accounts listing.

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?

No guidance on when to choose this over get_chart_of_accounts, get_account_ledger, or list_financial_years. The only usage note is mechanical (pagination and summarize.all_pages), not a selection rule between alternatives.

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