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

Annotations cover safety (readOnlyHint=false, destructiveHint=false, idempotentHint=true), and the description adds genuinely new behavioral context: the 'reconcile' permission requirement and the hard constraint that it can never attest. It does not describe state transitions beyond 'marked as prepared', so it is strong but not exhaustive.

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 core action and kept to a compact run of sentences, with no filler. It is dense, packing permission, scope, and argument semantics into one block, which slightly reduces readability but wastes nothing.

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 five-parameter mutation with no output schema, the description supplies the missing enum values, the account special case, the auth requirement, and the approval boundary. Only minor gaps remain (year/month format, returned state), which are low-stakes given annotations carry the safety and idempotency profile.

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 only 20% and contains no enums, yet the description enumerates the full bilaga_type vocabulary (BANK/AR_CONTROL/AP_CONTROL/VAT/AGI/TAX_ACCOUNT/ASSET/GL_ACCOUNT) and explains the non-obvious account='0 för aggregat som moms'. Year/month format remains unspecified, but the description substantially compensates for the schema gap.

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 ('Markera en bilaga som FÖRBEREDD') and explicitly anchors it to the app's 'Förbered' button, so the operation is unambiguous. It also carves out scope by declaring 'Kan ALDRIG attestera', separating it from the sibling approve/attest tools.

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 a clear usage context (equivalent to the Prepare button) and a prerequisite (key must hold the 'reconcile' permission), plus a boundary that attestation is a human four-eyes step. It stops short of naming an alternative such as revert_prepare_bilaga for undoing the action, so routing is implicit rather than explicit.

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