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

Annotations only declare readOnlyHint, and the description adds substantial context beyond that: a required schedule:shifts:read scope, opaque token pagination with no auto-crawl, an operational allowlist excluding payroll, national IDs, contact/health data and free-text comments, and an explicit no-writes/no-punches statement. This is exactly the behavioral disclosure an agent needs before calling.

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?

Front-loaded with purpose, then prerequisites, pagination, and exclusions in a compact paragraph with no filler. It is slightly dense and semicolon-packed, but every clause carries operational information.

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 read-only list tool with no output schema, the description covers auth, pagination, date-range constraints, and data-exclusion scope, and it notes the shape of the return (data plus tokens). The remaining gap is filter semantics for the optional ID/status parameters.

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?

With only 22% schema description coverage the description must compensate, and it does explain the required beginGte/beginLte window and the 93-day cap plus pageToken semantics. However, it is silent on idIn, statusIn, groupIdIn, employeeIdIn and deleted, leaving five of nine parameters with no guidance anywhere.

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 ('Read one bounded page of scheduled shifts'), and the resource (shifts) cleanly distinguishes it from every sibling, all of which operate on employees, groups, roles, or agreements. An agent can select it without opening the 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?

Gives concrete usage conditions: beginGte/beginLte are required here and must be at most 93 days apart, and continuation requires passing pageToken because there is no automatic crawl. It stops short of naming an alternative tool or stating when not to use it, so it lands just below the top band.

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