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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context beyond the annotations: the CSV is returned in the response text and "nothing is saved on the server," which tells the agent this is a stateless pure-compute call.

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 sentences, front-loaded with the purpose before the invocation details, and every sentence carries information (what, how to call, what comes back). Minor redundancy between "generated monthly schedule" and "the generated schedule," but nothing is padding.

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 an 8-parameter, nested-object tool, the description plus the rich schema-level object description (which names the required project/store/employees sections) covers what an agent needs to construct a call, and an output schema exists so return values need not be spelled out. The residual gap is the "schedule" vs "schedules" ambiguity and the unexplained auxiliary 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?

Property-level schema coverage is 0%, so the description must compensate, and it only covers the project and schedule placement. It says nothing about store, employees, preferences, availability, schemaVersion, or monthlyTargets. There is also a naming ambiguity: it references a top-level "schedule" property while the schema defines "schedules", which could mislead an agent about where to put the data.

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 (export), resource (monthly schedule) and output format (spreadsheet-compatible CSV), which is clear enough to distinguish it from rotase_generate_schedule and rotase_schedule_report. It does not explicitly name or contrast with rotase_schedule_report, which also produces schedule output, so differentiation is inferred rather than stated.

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 phrase "a generated monthly schedule" implies the precondition that a schedule must already exist (i.e., run rotase_generate_schedule first), and it explains how to supply that schedule to this call. It stops short of naming alternative tools or stating explicit when-not-to-use conditions.

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