design_mockup

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

With no annotations, the description carries the full burden and does add real operational context: the image model runs on the user's own Google account via GEMINI_API_KEY or NOTEFUL_VERTEX_PROJECT, and it returns the mockup path, mockup, and grid. It omits cost/latency implications of image generation, whether the mockup is persisted into a notebook or output folder, and how many reference names exist.

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 action and the payoff before parameters. Dense parameter walkthrough uses colons to pack a lot in, but the run-on 'content:'/'look:' clause is harder to scan than separate sentences would be.

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?

No output schema, yet the returns are described (path, mockup, grid); no annotations, yet auth and environment prerequisites are disclosed. A generative tool with cost and persistence implications would benefit from one line on where the mockup is written and whether repeat calls are expensive.

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 entirely, and it does: content is defined as page contents plus rough placement with the instruction to quote exact titles and labels; look gets both enum values, the default, and concrete visual meaning; theme lists light|dark; reference covers per-theme defaults and the 'previous page's mockup path' consistency case.

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?

States a specific verb and resource ('Draw a picture of a study page with an image model') and ties it to its downstream consumer, design_page, which converts the mockup into ink. That contrast alone distinguishes it from siblings like design_page, clean_copy and render_page.

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 real decision guidance: default to 'calm' and reserve 'rich' for visual summary pages, with an explicit warning that a notebook full of rich pages looks overdone. Reference defaults are conditioned on theme (clean-copy for rich light, answers-tree for dark, none for calm). It does not name siblings such as example_pages for browsing the gallery, so the 'gallery example name' reference is left slightly ungrounded.

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