Apply an app recipe

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

Annotations already declare non-readonly, idempotent, non-destructive, open-world, but the description adds substantial context beyond them: it leaves existing names unchanged, ensures the background service unless no_daemon_install is true, and discloses the never-public Funnel refusal policy requiring force_unsafe_public plus public_ack. The scope boundary about not configuring/installing/probing the app is genuinely useful behavioral disclosure.

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?

Four sentences, front-loaded with the core action, then prerequisite, then policy caveats. Every sentence carries weight, though the ordering mixes invariant behavior (name preservation) with safety policy in a slightly dense way.

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 complex 16-parameter tool with nested objects, the description covers the workflow prerequisite, primary side effects, and the highest-risk policy gates. An output schema exists so return values need not be described. Remaining gap is minor parameters not addressed, but the risky surface is well covered.

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?

With 63% schema coverage, the description compensates meaningfully by explaining key parameter interactions: no_daemon_install governs daemon installation, force_unsafe_public requires funnel and public_ack, and Funnel is refused for never-public apps. Some parameters (ephemeral, no_auto_provision, control_url) remain undocumented in both places, but the critical policy parameters are clarified.

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 — applying a reviewed recipe plan to the registry — and explicitly scopes what it does not do (does not configure, install or probe the third-party app). It clearly separates itself from recipe_plan (must be called first) and recipe_list. An agent can identify the operation without opening the schema.

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?

Names the prerequisite sibling explicitly ('Call recipe_plan first') and implies the workflow is only valid on an already-reviewed plan. It does not, however, contrast against other apply-type siblings such as template_apply, so the routing is strong but not exhaustive.

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