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

With no annotations, the description carries the burden and does disclose real behavior: the toggle's meaning in each direction and the scheduling consequence of re-enabling ('it next runs at its next slot from now'). It omits permission requirements and what happens to an in-flight run, but the core state semantics are covered.

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 tight sentences with the action front-loaded, the boolean semantics immediately after, and the identifier hint at the end. No filler; the Agents-page analogy does real work compactly.

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 and no annotations mean the description is the only behavioral source, and it covers the toggle well. However, the unexplained `agent` parameter leaves ambiguity about whether routines are scoped per agent and how name lookups resolve – a real gap for a 3-parameter mutating tool.

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 0%, so the description must compensate. It adequately explains `routine` (id or name, pointing to list_routines) and `paused` (true/false meaning), but leaves the `agent` parameter entirely unaddressed, so the third parameter remains undocumented 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 ('Pause one of the user's routines') and clarifies it is a bidirectional toggle via the paused flag. It is clearly distinguishable from delete_routine/list_routines by implication, though no sibling is named explicitly as an alternative.

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 clear context for either direction of use (paused: true vs false) and anchors the semantics to a familiar UI control ('as its switch on the Agents page does'). It does not state exclusions or contrast with update_routine, which would be the natural alternative for non-toggle edits.

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