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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so 'Läser bara, ändrar inget' largely restates them. However, the description adds genuinely non-obvious behavior beyond the annotations: the stable id contract (ref reused as finding_ref in create_proposal and book_voucher) and the exact return payload per finding.

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 the purpose, then scope, then the sibling alternative, then the return contract. Dense and largely waste-free, though the enumeration of return fields is long; still, each sentence carries information an agent needs.

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?

There is no output schema, yet the description compensates by enumerating the return fields and explaining the ref identifier's downstream role in create_proposal and book_voucher. Combined with annotations and a fully described single parameter, an agent has everything needed to call this 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 100% and the sole parameter (orgnr) is fully documented in the schema, including format and how to obtain it via list_companies. The description adds no parameter-level detail, so the baseline of 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 (avvikelser), and immediately scopes it as exceptions the reconciliation could not resolve automatically, each with a proposed correction. It explicitly distinguishes itself from the sibling get_open_reconciliations, which handles monthly reconciliations.

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 and when-not-to-use: applies to the whole latest fiscal year, not a single month, and names the alternative (get_open_reconciliations) for monthly reconciliations. Nothing 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.