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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, so safety is covered. The description adds lifecycle context beyond that: the data stays unhandled until booked or sorted away, and records are returned oldest-first. The closing 'Läser bara, ändrar inget' largely restates the annotation, so it stops short of 5.

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 purpose, then lifecycle, usage routing, return format, and safety in a tight sequence. It is dense and runs long, but nearly every clause carries routing or return-value information, so waste is minimal.

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 no output schema, the description carries the return contract fully: integrations with count per compartment and status, plus records (oldest first) with id, source, kind, date, heading, amount in öre, status, and summary. Combined with annotations and full schema coverage, nothing an agent needs is missing.

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%, so every parameter (provider, kind, status, dates, limit, offset) is already documented in the schema. The description hints at the compartment/kind grouping and oldest-first ordering but adds no syntax or format detail beyond what the schema provides; baseline 3 applies.

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 (listar) and resource (data från kopplingar) with concrete examples (Shopify-ordrar, Stripe-betalningar), and explicitly frames the data as unhandled integration data. An agent can distinguish it from siblings like get_integration_record or resolve_integration_records without opening any schema.

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?

Gives explicit triggers (when list_companies or get_overview shows unhandled integration data, or when the user wants to bookkeep sales/payouts) and names the alternatives with their conditions: get_integration_record for record detail, resolve_integration_records when the record is booked.

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