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

With no annotations provided, the description carries the full burden and does so richly. It discloses auto-slugification and collision handling, columns being ignored for doc/html, html surfaces starting empty, files starting empty with a note about human file upload, the editor role requirement, and the emitted surface.created event. This is far beyond a minimal 'creates a surface.'

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 a single dense paragraph that front-loads the purpose, then systematically covers kinds, optional parameters, and per-kind behavior. Every sentence contributes useful, non-redundant information, and there is no fluff or repetition.

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?

The description covers many behavioral aspects (roles, events, kind-specific details) but misses a critical piece: how to specify the target workspace. The required `slug` parameter is not addressed at all, and the misnamed `slug`/`surface_slug` confusion further harms completeness. With no output schema, the description also does not state what the API returns, though the emitted event is mentioned.

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 uses `slug` to refer to the optional surface slug but the schema's `slug` parameter is required and is the workspace slug, while the actual optional surface slug parameter is `surface_slug`. This misnaming directly contradicts the schema and can mislead an agent into thinking the required `slug` is optional. It also fails to mention the required workspace slug parameter at all, offering no guidance on how to specify the workspace. Despite 100% schema coverage, the description's parameter explanation is actively harmful.

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 clear imperative 'Create a new surface (tab) inside a workspace,' specifying the verb and resource. It also differentiates from siblings like 'update_surface' and 'create_workspace' by enumerating the four surface kinds and their distinct behaviors.

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 context on when to use the tool and gives tool-specific alternatives for downstream actions: html surfaces should be written via update_html, files surfaces browsed via list_files/get_file/list_recent_files. It also notes the editor role requirement and the agent byte-upload limitation. However, it does not explicitly state 'use this instead of update_surface for creation,' though that is implied.

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