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

Annotations only supply destructiveHint=true, so the description carries the rest: it discloses that shifts are unpublished by default and become employee-visible only once published, plus the underlying POST /shifts endpoint. This is meaningful behavioral context an agent needs, though it omits permission/auth requirements.

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 short, front-loaded sentences with zero filler; the mutation type, key parameter rule, and default visibility are all stated efficiently.

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For a write tool with no output schema, the description covers the essentials: create semantics, default unpublished state, open-shift handling. It stops short of explaining return values or auth needs, but the rich schema compensates.

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 all 8 parameters are already documented. The description's only parameter note ('leave user_id out for an open shift') essentially duplicates the schema's own 'omit for an open shift', adding little beyond the baseline.

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 ('create a shift on the rota') with a 'WRITE:' prefix that flags it as a mutation. It is clearly distinguishable from update_shift and list_shifts by verb, though it names no sibling explicitly.

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?

'Leave user_id out for an open shift' gives conditional usage for one parameter, and the publish note clarifies the default state. However, there is no explicit when-to-use vs. alternatives (e.g., update_shift vs. create_shift) or any exclusions.

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