Metis — Viz Library Overview

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

With no annotations, the description does the safety work itself: 'Show' and the absence of any mutation language make clear this is a read-only enumeration. It adds genuinely useful non-obvious context — that the same text is exposed as the `metis://viz-styles` resource — which tells the agent there is a mirror surface with identical content. Minor gap: no mention of size/volume of the payload or cost of dumping the whole library.

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 verb and scope, then the trigger, then the mirror-resource note, then the return shape. Only the resource sentence is arguably meta, but it earns its place by preventing client-specific duplication work. Slightly long for a zero-argument read tool.

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 zero-parameter read tool this is fully adequate: what it returns (styles with loved-render counts, recipes with data contracts and track records), when to call it, and the resource mirror are all covered. The output schema exists, so the extra return summary is surplus rather than a requirement, and nothing an agent needs is missing.

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 tool takes zero parameters, so the baseline of 4 applies; there is nothing for the description to disambiguate. The description correctly implies no arguments are needed to get the full library.

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 ('Show the whole visualization library — every style, every recipe'), and the scope word 'whole' plus the enumerations distinguish it from the sibling search tool find_viz and the individual save_viz_style/save_viz_recipe tools. An agent can identify it as the browse-everything entry point without opening any schema.

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?

Explicit trigger given: 'when the researcher asks what styles exist, or before offering a choice of look' — this is a clear when-to-use condition tied to a concrete conversational situation. It stops short of naming alternatives (e.g. find_viz for targeted lookup, check_viz_fit for fit evaluation), so the routing is clear but not exclusionary.

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