Create screen

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

Annotations already mark readOnlyHint=false, so the write nature is clear. The description adds meaningful behavioral constraints: the unique combination of model_id and name, and the unsupported remote URI modes. No contradiction with annotations.

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?

Three short, front-loaded sentences. The first states the core purpose, the second gives a required prerequisite, and the third adds constraints. No unnecessary words.

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?

While the description covers some key constraints, it omits important operational details: what the response looks like, possible errors (e.g., uniqueness violation), and the meaning of label vs. name or playlist_id. With no output schema, the agent is left with significant uncertainty.

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 only 17%, with only 'mode' explained. The description clarifies html as a complete Framework document and mentions name/model_id uniqueness, but leaves label, playlist_id, and model_id semantics unexplained. With such low schema coverage, the description must compensate more heavily.

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 opens with a specific action, 'Render a new Terminus screen,' and clarifies the required input as 'a complete Framework HTML document.' This clearly distinguishes creation from sibling tools like update_screen or list_screens.

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?

Provides an explicit prerequisite ('Read terminus:screen-authoring first') and a uniqueness constraint for model_id/name. It also states an exclusion ('Remote URI screen modes are not exposed'). However, it does not explicitly name alternative tools for updates, stopping short of a 5.

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