generate_bookmark

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

With no annotations, the description carries the full burden, and it does disclose meaningful behavior: an inline 3D stage is opened on success, hosted sessions get a browser stage link, oversized meshes are auto-decimated, and there is a 3/month free-tier quota. It does not say whether the generated bookmark is persisted as a design, whether the call is idempotent, how failures surface, or what is returned besides a PNG preview.

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 purpose is front-loaded correctly in the first sentence, but the inline 3D stage behavior is described twice (opening sentence and the 'INLINE 3D STAGE' block), and a pricing/upgrade URL occupies a standalone line. The 'MAKE DOORS' paragraph is the longest section yet is about other tools rather than this one.

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 12-parameter, all-optional generative tool with no output schema, the description should clarify what comes back (artifact path, design id, preview URL) and what the spare parameters do. It covers the visual stage and quota but leaves the unit/format ambiguity of `size`, `brief_id`, and `color_overrides` unaddressed in both schema and description.

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 reported at 100%, so the baseline of 3 applies. The description explains only the two most consequential knobs conceptually ('decoration', 'page clip' → clip_depth_mm); it adds nothing about `size`, `brief_id`, `material`, `corner_style`, `color_overrides`, or acceptable value formats for the six string parameters.

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 opening sentence gives a specific verb and resource ('Generate a bookmark') plus the differentiating capabilities ('optional decoration and page clip'), which separates it from the many other generate_* product siblings by object type. It also names the general-purpose making paths it is not (`design_session`, `compile_scad`), though that routing block slightly blurs whether this tool or compile_scad is the intended entry point.

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 'MAKE DOORS' paragraph tells the agent that `design_session` is unavailable on this install and that `compile_scad` is the general make → preview → iterate loop, which is real routing context. However, it never states the condition under which an agent should pick `generate_bookmark` over `compile_scad`, `generate_keychain`, or `generate_coaster`; usage is only implied by the product name.

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