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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the safety profile is covered. The description adds real value beyond that: it discloses a plan-key prerequisite ('Requires an Advance plan key') and states the operation produces a switched-off draft rather than an active recipe, which is important behavioral context for a mutation tool.

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 short sentences with no waste. The prerequisite and the outcome are front-loaded, so an agent can assess eligibility before reading further.

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?

The definition covers the key facts an agent needs: plan requirement, resulting draft state, and full parameter documentation via the schema; no output schema exists so return values need not be explained. Slightly incomplete in that it doesn't say what happens if the recipe key is invalid or whether re-installation overwrites an existing draft.

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 100%, so every parameter is already documented (including cross-references like list_recipes and list_connected_apps). The description adds no parameter-level detail beyond what the schema provides, so the baseline of 3 applies.

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 uses a specific verb ('installs') and resource ('recipe as a switched-off draft'), and clarifies the resulting state (inactive, awaiting owner review). It implicitly distinguishes the tool from create_automation_draft by scoping it to recipes, but never names the sibling explicitly.

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?

The phrase 'for the owner to review' implies this is a staging/draft step rather than an activation, which gives some usage context. However, there is no explicit when-to-use guidance, no when-not conditions, and no named alternative (e.g., a publish or activate tool).

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