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

The description adds meaningful behavioral context beyond the annotations: write scope is required, creation is impossible, and comment_to_dm is limited to enabled-only changes. The annotations already declare destructiveHint and idempotentHint, so the description does not need to restate those, but it could have said more about the response or the empty-steps behavior.

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?

The description is front-loaded with the core actions, then adds the creation restriction and the comment_to_dm limitation. Every sentence contributes operational guidance, 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?

Given the rich schema and annotations, the description is nearly complete for correct invocation: it covers creation restrictions, write scope, and recipe-specific limits. It does not explain the result of the mutation or what happens when only recipe_key is supplied, which are minor remaining gaps.

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 100%, so the schema already documents all three parameters. The description still adds useful cross-parameter semantics, especially that comment_to_dm content cannot be modified through this tool and that steps relate to reengagement_48h replacement.

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 specific actions (activate/deactivate an existing recipe, replace reengagement_48h step content) on a specific resource-type (automation recipe). It explicitly distinguishes itself from creation by saying it never creates a recipe and must target one that already exists.

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 gives clear conditions: use it on an existing recipe, never for creation, and configure a recipe first in Ficiel if needed. It also states the important boundary that comment_to_dm can only be toggled via enabled here, while its content is configured in the UI.

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