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

Goes well beyond the annotations (readOnly=false, idempotent=true, destructive=false) by disclosing the side effect that records leave the unhandled set and stop being flagged, the required 'book' permission, and the return shape ('Returnerar posterna med ny status'). It also forbids booking within this call, which is essential for a status-mutation tool. No contradiction with the annotation profile.

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-loads the action and the three possible states, then sequences prerequisites, prohibition, return value, side effect and permission in descending priority. Every sentence carries information; no filler.

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?

For a multi-record mutation with no output schema, the description covers the mutation semantics, the prerequisite workflow, the authorization requirement, the side effect, and the return value. An agent has everything needed to invoke it 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 description coverage is 100%, so the schema already explains orgnr, record_ids (max 500), status, voucher_ids and note. The description adds contextual meaning for voucher_ids (linking the record to the booking) and restates the three status values, but no syntax or format detail beyond the schema. Baseline 3 is correct.

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 ('Markerar poster från en koppling') plus the full set of target states (handled/ignored/new), and it names the sibling it is not — list_integration_data for reading and the 'vanliga verktygen' for booking. An agent can distinguish it from every booking or lookup sibling without opening a 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?

Explicit when-to-use ('Använd efter att du bokfört posterna med de vanliga verktygen'), how to supply the link ('ange verifikatens id så att posten pekar på bokföringen'), an explicit prohibition ('Bokför ingenting själv'), and a named alternative for the read path (list_integration_data). Nothing about selection is left to inference.

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