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

Annotations already declare destructiveHint=true and readOnlyHint=false, so safety is partially covered; the description adds genuine behavioral context beyond that: cadence edits recompute the next fire time, and enabled functions as a pause/resume switch. It still doesn't say whether omitted fields are preserved, whether changes need confirmation, or what the approval envelope requires.

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 short clauses, all front-loaded with the highest-value facts first (what can be updated, then partial-update rule, then side effect). No filler or restatement of the 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?

For a 12-parameter mutation with no output schema, the description covers the core concepts, the partial-update contract, and the main side effect, which is the bulk of what an agent needs. Gaps are the delivery=room/roomId dependency and the approval-confirmation flow, though both are partly documented in the schema.

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 only 42% across 12 parameters. The description adds conceptual meaning for the undocumented enabled, delivery, and instruction fields, but it lumps four separate schedule parameters (interval, scheduleTime, scheduleDayOfWeek, scheduleTimezone) under the single word "cadence" without mapping them, and stays silent on name, roomId, workspace, and approvalId.

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?

The description states a specific verb and resource and enumerates the mutable surface (instruction, cadence, delivery, enabled/pause-resume), so an agent immediately knows what can be changed. However, it never points at the sibling it complements (routines_list to discover ids, routines_create as the alternative), so differentiation is left to inference from the verb.

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?

"Only pass the fields being changed" is an explicit and valuable partial-update invocation rule, and "(pause/resume)" clarifies the intended use of the enabled flag. There is no when-not guidance and no prerequisites around the approval/confirmation path that the approvalId parameter implies.

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