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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description's added value is behavioral: it discloses that results are paginated one page per call and that summarize.all_pages must be set to get cross-page totals. It says nothing about auth, rate limits, or what happens with expand, so the added context is useful but thin.

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 the purpose front-loaded and pagination behavior immediately after; no filler. The bare URL in parentheses is slightly noisy but functions as a source-of-truth pointer.

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?

With eight parameters, a nested summarize object, and an output schema present, the description only needs to cover call semantics rather than return shape — and it does cover pagination and aggregation. Gaps remain around expand's effect on payload size, fields projection, and sortby validity, which are relevant to invoking the tool correctly.

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 63%, so several of the eight parameters (page, limit, offset, expand beyond its terse schema note) rely on inference. The description reinforces the page/limit semantics via "one page per call" and clarifies the nested summarize.all_pages flag, which is more than the schema alone provides for that sub-field, but it leaves half the parameters untouched.

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?

The description restates the title ("Retrieve the Company Information") and adds only the underlying Fortnox endpoint, GET /3/companyinformation. The verb+resource is identifiable, but there is no differentiation from nearby siblings such as get_connected_company, get_client_overview, or list_connected_companies, so an agent cannot tell why it would pick this one over those.

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 real guidance on pagination and when to escalate to server-side aggregation. However, there is no statement of when to use this tool versus the many other company/overview tools, and no exclusions or prerequisites.

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