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

Annotations declare only readOnlyHint=true, so the description carries the rest and does so well: it enumerates the returned record fields (StartTime/EndTime, StartTimeLocalized, OperationalUnit, Published, Open, Cost, _DPMetaData with names) and clarifies that Employee is 0 or null for open shifts. It also discloses the underlying Deputy call. It stops short of describing result ordering or pagination behavior beyond the schema's start/max.

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?

Two compact sentences: the first front-loads purpose and filters, the second enumerates the record shape, with the Deputy endpoint tacked on as a reference. No filler or restatement of the tool name.

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?

No output schema exists, and the description compensates by listing the returned fields and the open-shift sentinel values, which is exactly what the agent needs to interpret results. With no required params and a clear read-only annotation, the remaining gaps (ordering, total counts, pagination loop details) are minor.

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 every parameter is already documented with types, ranges and Deputy-specific semantics (next_start paging, 1-500 cap). The description only adds the Employee=0/null tie-in to the open flag, which is marginal beyond what the schema provides. 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 (Search) and resource (the roster / scheduled shifts) plus the filter dimensions it accepts: time window, employee, area, and published/open state. This cleanly separates it from deputy_get_shift (single shift) and deputy_list_timesheets without the agent needing to open a schema.

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?

Usage is only implied through the enumerated filters; there is no explicit when-to-use or when-not-to-use guidance, and no sibling is named as an alternative (e.g. get_shift for a single shift, publish_shifts for state changes). Adequate for an agent that reads schemas, but no routing help.

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