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

Annotations only supply generic destructiveHint/idempotentHint flags; the description adds the substance behind them — that the default path destroys nothing but actively preserves history, that hard=true is a true erase, and that a precondition (no payroll runs) gates it. It also names the required auth scope (payroll). This is exactly the extra context annotations cannot convey.

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?

Four short sentences, front-loaded with the core soft/hard distinction and the constraint before the trailing argument list. The final 'Argument: orgnr, employee_id; valfritt hard' clause is largely redundant with the schema, costing it a point.

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 mutation tool with no output schema, the description covers purpose, the two behavior modes, the gating precondition, and auth scope. It leaves open what a blocked hard delete actually returns (error vs. silent fallback to soft) and whether a confirmation payload exists.

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 33% (hard has no description, employee_id has none). The description compensates for the most important gap by defining what hard toggles — false/absent = deactivate, true = permanent delete with a guard. It does not explain employee_id format, but the one semantically ambiguous parameter is fully covered.

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+resource (delete/deactivate an employee) and goes further by naming the two operating modes, soft (utan hard) and hard. It is unmistakable what the tool does, though it never references a sibling tool to differentiate itself (upsert_employee, list_employees) — not that a direct alternative really exists for deletion.

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 real conditional rule: omit hard to deactivate while preserving history, set hard=true to fully delete but only when the employee has no payroll runs. This is clear when-to-use guidance. It falls short of a 5 only because it names no alternative tool or fallback path when hard deletion is blocked.

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