trmnl_import_user_theme

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

Annotations already flag destructiveHint=true, idempotentHint=false and openWorldHint=true, and the description adds genuinely useful context: the underlying POST /api/user_themes/imports endpoint, the parse path shared with createUserTheme, and the account-level prerequisite. It does not, however, explain the destructiveness the annotation asserts — nothing says what happens if a theme with that name already exists or whether an existing theme is overwritten. The trailing "Run only within the user-authorized scope" is generic boilerplate rather than tool-specific 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 core action and its scope lead the description, and the shared-parse detail is a useful second sentence. The raw endpoint reference plus the generic mutation warning at the end are template filler that don't earn much space, but the whole thing stays short.

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 non-idempotent, destructive write with no output schema, the description covers origin of input and the enablement prerequisite but leaves the return value and the failure/overwrite semantics unspecified. An agent knows how to call it, but not fully what it will do to an account that already has a theme with that name.

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 50% (the nested body object and the profile parameter carry no schema descriptions), so the description has to carry weight — and it does clarify token semantics (a share link decoded through the settings parse) and that the result is saved under name. It says nothing about the profile parameter or how name collisions are resolved despite the schema's "Unique per account" note.

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?

Names a specific verb and resource ("Create a theme from a shared theme snippet") and pins down the exact input form: a /t/:token share link decoded through the same parse path createUserTheme uses, then saved under name. That distinguishes it cleanly from the sibling trmnl_create_user_theme, which builds a theme from settings rather than from a share token.

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?

Gives a concrete precondition ("Requires the theme builder to be enabled for the account") and implicitly scopes usage to cases where the user has a share link in hand. It stops short of stating when NOT to use it — e.g. when the caller already has raw theme settings, in which case trmnl_create_user_theme is the right sibling.

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