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

Annotations cover safety and idempotency, and the description adds real behavior outside the annotations: the publish-check gate on activation, the refusal semantics ("a refusal says what is missing"), and the side effect that deactivating ends runs in progress. That last point is important context the agent would otherwise have to guess at. It doesn't cover authorization requirements or what a successful response contains, so it isn't fully exhaustive.

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 sentences, front-loaded with the core action, then consequences, then parameter provenance, then the retry instruction. Nothing is redundant with the title or 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 a 3-parameter mutation with no output schema, the definition covers what changes, what can go wrong, and how to retry safely. The remaining gap is minor: the on/off meaning of the boolean parameter is implied rather than stated.

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 33%, so the description must carry more weight, and it partially does: it gives the provenance of flow_id (read('flows')) and restates the retry contract for idempotency_key that the schema already documents. The boolean is_active is never explicitly mapped to the on/off behavior, so an agent must infer which flag value activates versus deactivates the flow.

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 ("Turns a flow on or off") and anchors it to a concrete referent ("the On switch on the Automations page"). This distinguishes it from set_flow_archived, set_flow_start and edit_flow, which operate on the same resource for different purposes.

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?

It clearly frames when this applies (Activating a flow): turning it on triggers a publish check that can refuse, while turning it off terminates in-progress runs, so the agent can predict consequences before calling. It also routes discovery ("flow_id comes from read('flows')") and says how to retry. It stops short of naming sibling alternatives such as set_flow_archived for retiring a flow, so some selection logic is left to inference.

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