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

Even with destructiveHint=true, description adds precise destructive scope: clears TODAY'S pending drafts but preserves approved/published. It also discloses that switching reseeds a starter config, which agents need to know before calling.

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 dense sentences pack purpose and per-flow config rules without filler. Front-loaded with action and effect, then compact field mapping.

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?

Description gives purpose, side effects, and per-flow config constraints enough to call. It doesn't describe return value/errors, but no output schema exists and expected response for a mutation tool is less critical; could add a note on get_flow for reading current config.

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 covers constraints, but description adds per-flow field mapping ('recycle → source_post_indices + slots_per_day'), date ordering, and asset existence requirement. It doesn't repeat handle/context since those are already well described in schema.

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?

Description opens with specific verb 'Switch' and resource 'the tenant's daily flow and/or patch its configuration', then details the consequence (reseeds starter config, clears pending drafts). This clearly differentiates set_flow from read-only get_flow and other sibling tools.

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 distinguishes two usage modes (switching flow vs patching config) and indicates flow omission preserves current flow. It lacks explicit 'use get_flow to read current' or exclusions relative to set_automation, but the per-flow mapping gives strong contextual guidance.

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