trmnl_install_recipe

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

Annotations already declare the mutating, open-world, non-idempotent, non-destructive profile, and the description adds real context beyond that: installs are governed by install_method, they mutate account state, and device_id extends the effect to a device playlist. It still does not explain what happens on a repeat install (non-idempotent) or any OAuth/inherit_oauth implications, which is the main residual gap.

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 verb and the core behavior are front-loaded in the first two sentences, and the endpoint line is compact. The trailing 'Changes remote state or starts work. Run only within the user-authorized scope' reads as boilerplate that adds little, keeping it from a 5.

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 mutating tool with no output schema, the description covers the operation's mechanism, the conditional device effect, and the endpoint, which is enough to call it correctly. Missing are the repeat-install outcome and whether a follow-up completion step is ever required, given the installation-lifecycle siblings.

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 only 33%, so the description must carry weight; it does explain the conditional effect of device_id (playlist membership only when provided), which the schema does not. However, it says nothing about inherit_oauth or the profile parameter, leaving those to the schema's own brief descriptions.

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 a specific verb and resource ('Install a recipe') and immediately explains the two effects: it installs into the account according to the recipe's install_method, and adds to a device playlist when device_id is supplied. This clearly separates it from trmnl_get_recipe and trmnl_search_recipes, though it does not distinguish it from the related installation-lifecycle siblings (prepare_installation, complete_installation).

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 reference to 'getRecipe's install_method' implies the agent should read the recipe first to learn how installation behaves, but this is only an implication. There is no explicit statement of when to use this versus trmnl_install_app or the prepare/complete installation tools, and no stated preconditions beyond the generic 'user-authorized scope' line.

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