Create Override Recommendation

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

Annotations declare readOnlyHint=true, destructiveHint=false and openWorldHint=true; the description reinforces the read-only claim by promising a recommendation list plus a 'ready-to-use override payload' rather than a mutation. It adds real behavioral content the annotations do not: candidates are filtered by load, results are sorted lowest-load-first, and a top pick is pre-assembled. No auth, rate-limit, or empty-result behavior is described.

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 purpose and followed by the ranking rule and the return shape. No filler, though the phrase 'ready-to-use override payload' could have been spent naming the tool that consumes it.

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?

An output schema exists, so return values do not need spelling out, and the read-only safety profile is covered. However, a recommendation-only tool whose output is explicitly a payload omits the single most useful piece of context: which tool to call with that payload. The agent is left to infer the create_override_shift handoff.

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 the schema already documents all five parameters including exclude_user_ids. The description adds conceptual context — that the date period and schedule drive the load calculation — but never references a parameter by name or clarifies how exclude_user_ids interacts with the load filter. Baseline 3 applies.

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: 'Recommend replacement responders for an override shift', then narrows the candidate pool to users in the same schedule rotation who are not heavily loaded. The critical disambiguation — that despite the 'create_' prefix this only recommends, returning a payload rather than writing anything — is conveyed. It stops short of naming create_override_shift as the sibling that actually performs the write.

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?

The scenario is implied clearly (you need a replacement for an override shift), but there is no explicit when-to-use vs when-not, and no alternative is named. Given siblings create_override_shift and check_responder_availability exist, the agent must infer the division of labor between 'recommend', 'check availability', and 'create'.

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