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

Adds substantive behavior beyond the destructiveHint annotation: default DRAFT state, that publishing can notify the employee, and that success returns an empty 200 body. These side-effect disclosures are exactly what a create tool needs, though it never explains why destructiveHint is true (e.g. force_overwrite clobbering).

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: what it does, the default/notification behavior, and the empty-response workaround plus endpoint. No filler, front-loaded with the action.

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, and the description compensates by explaining the empty 200 response and the follow-up call needed to obtain the id — the single most important gap for a create tool. Combined with the annotation and full schema coverage, nothing essential is missing.

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%, so all ten parameters are documented in the schema; the description only restates the publish/open semantics already present in the parameter descriptions. Baseline 3 is appropriate since the schema carries the parameter burden.

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?

Specific verb (Add) plus resource (a shift to the roster) with scope details: assigned to an employee or left open. The name/create intent is unmistakable and clearly separable from deputy_update_shift and deputy_publish_shifts.

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?

Explains the draft-vs-publish decision point and tells the agent to use deputy_list_shifts afterward to recover the new shift id, which is real workflow guidance. It does not explicitly contrast with siblings like deputy_update_shift or deputy_publish_shifts, so it stops short of full routing guidance.

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