create_ui_page

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does add useful details: pages are appended last, reordering is delegated to set_default_ui_page, and item commands are validated first. However, it fails to mention that dry_run defaults to true, meaning a default call may not persist the page at all, which is a critical behavioral omission for a creation tool.

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 description is compact at four sentences, front-loads the primary action, and every sentence adds necessary information. There is no filler or redundant repetition of the schema.

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?

Given seven parameters, nested objects, and no annotations, the description is insufficient for safe invocation. It omits the dry_run default, the meaning of scope_id and name, the host field, and any prerequisites about the target activity or remote-entity. While an output schema exists and return-value details are not required, the missing behavioral and parameter context is significant.

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 0%, so the description must compensate. It explains scope values, the grid shape, and that items match get_ui_page output, which is genuinely helpful. But it leaves required parameters like scope_id and name, plus optional host and dry_run, completely unexplained, so an agent cannot confidently populate all inputs.

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 verb and resource: 'Add a new page to an activity or remote-entity.' It also clarifies the two valid scope values and distinguishes this operation from related siblings like update_ui_page, delete_ui_page, and set_default_ui_page. There is no ambiguity about what the tool does.

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 description gives clear context for when to use the tool by stating the target types and scope values. It also directs the agent to set_default_ui_page for reordering, which is a useful alternative boundary. However, it does not explicitly say when not to use it or mention update/delete as alternatives for modifying existing pages.

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