trmnl_create_device_mashup

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

Annotations already declare the mutation profile (readOnly=false, idempotent=false, destructive=false, openWorld=true), so the description's 'changes remote state' line largely echoes them. It does add useful behavior not in annotations: positions omitted from contents render empty, and the 1x1 layout silently produces a different object type. It says nothing about duplicate handling, ordering effects on the playlist, or required permissions.

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?

Front-loaded with the core action, then the behavioral exception, then the endpoint. Every line is relevant, though the trailing 'Changes remote state or starts work. Run only within the user-authorized scope.' is generic boilerplate that adds little for this specific tool.

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 nested-body mutation with no output schema, the description covers the conceptual model and where to look up valid values, which is the critical part. It omits what the call returns, whether the new item is appended or replaces anything, and error conditions for an invalid layout/position combination.

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?

The description adds real guidance beyond the 33%-covered schema by pointing at getDevice as the source of valid layouts and positions. But the third parameter (profile) and the grid_config semantics (3x3-only cells) are left entirely to the schema, and the description does not restate what contents keys mean at the playlist level.

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 opening line gives a specific verb+resource ('Add a mashup to a device playlist') and the follow-up explains the concept ('Splits one screen between plugin settings'), which disambiguates mashup from a normal playlist item. It also distinguishes itself from the plain-item path by noting the 1x1 layout fallback, though it never contrasts with sibling tools like trmnl_update_mashup or trmnl_get_mashup_options by name.

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?

Clear context for when the mashup path applies and an explicit exception (1x1 layout creates a plain playlist item instead), which routes the agent to a different behavior. It stops short of naming the sibling tool to use for that plain-item case (trmnl_add_device_playlist_item) or when to prefer trmnl_update_mashup over creating a new one.

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