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

Annotations already flag this as destructive, non-read-only, and idempotent, so the safety profile is covered. The description adds genuinely new behavior: the employee is typically notified, existing assignments are overwritten rather than erroring, and the response contains the shift's assigned and applied users. It does not explain what exactly the destructive action destroys or what permissions are needed, so not a 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?

Three tight sentences plus an endpoint, with the operation mode and core action front-loaded. No filler; each clause carries distinct information (mode, effect, side effect, return value).

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 usefully states what comes back (assigned and applied users) and discloses the notification side effect and idempotent re-assignment. It is nearly complete for a 3-parameter write tool; only permission requirements and failure conditions are absent.

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 user_id and shift_id are already documented, establishing a baseline of 3. The description's note about application=true only restates the schema's own wording ("record as an application instead of assigning directly"), adding little new semantics.

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?

Opens with a mode tag ("WRITE:") then a specific verb+resource: "put an employee on a shift," plus the alternate application mode. This is clearly distinguishable from read-side siblings like papershift_list_shift_assignments or papershift_get_shift.

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 clear situational context: use it to assign, and pass application=true to record an application instead of a direct assignment. It also states that re-assigning an already-assigned user is allowed, removing a common ambiguity. It stops short of naming an explicit alternative or exclusion (e.g., when to prefer list_shift_assignments for verification).

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