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

The key non-obvious behavior — partial-update semantics where "any cadence field left out keeps its current value" — is disclosed and exemplified with the 9am→10am case, which the annotations do not convey. It also frames pause/resume as reversible versus delete, which softens but does not contradict destructiveHint=true; the only gap is that permission requirements and any side effects on in-flight runs are unstated.

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 sentences, each doing distinct work: scope, the pause-vs-delete decision, the partial-update rule with an example, and id provenance. The most decision-relevant information is front-loaded with no filler.

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 7-parameter mutation tool with no output schema, the description covers what to change, how partial updates behave, and how to obtain the required id. It stops short of describing what the tool returns or what happens to a currently-running schedule when paused or rescheduled.

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 coverage is only 57%, but the description compensates for the most consequential gap by explaining PATCH-style defaults (omitted fields retain current values) and giving a worked example with hour=10. It does not clarify cadence transition rules (e.g., whether switching to weekly requires weekday) or timezone behavior, which remain undocumented in both places.

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 ("Change an existing schedule") and enumerates the three concrete operations: pause, resume, or reschedule. It also implicitly separates itself from delete_schedule by explaining that deletion "throws away the setup," so an agent can tell the two apart without opening either 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?

Explicitly names the decision rule: use pause when someone wants a schedule to stop for now, use delete only when the setup should be discarded. It also tells the agent where the required id comes from (list_processes), closing the most likely failure mode.

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