Get Illustration Guide

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

Annotations already declare this a read-only, idempotent, non-destructive, closed-world lookup, so the safety profile is covered. The description adds real behavioral knowledge beyond that: the guide is topic-indexed, an empty call returns an index rather than content, and the flow terminates in review-illustration with style "isometric". It does not describe the returned guide's format or size, which keeps it from a 5.

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 purpose, then usage, then a scannable topic list, then the call recipe — the ordering serves the reader well and every topic line carries information. Minor waste: the internal tracker reference '[BD-1143]' means nothing to an agent, and 'coloured by the design system' / 'the card, the live readout, motion and accessibility' are terse to the point of being cryptic.

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-required-parameter, read-only guide loader with no output schema, the description covers what an agent needs to start: what the guide is, when to use it, which topic to pick, and how to iterate to the review step. The only gap is that nothing says what a loaded guide actually returns (format, approximate length), which matters since there is no output schema to fall back on.

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 100%, so baseline is 3. The description still earns credit by enumerating all seven topic values with a one-line gloss each (isometric-concept, -parts, -camera-and-depth, -lines, -card-and-motion, -kit, -review), which tells the agent far more about the `topic` parameter than the schema's two bare examples do. `query`, `context` and `maxTokens` are left entirely to the schema.

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 ('Load Better Design's guide') plus a precise subject domain ('an isometric drawing of a small machine whose working is the idea, instead of boxes and arrows'). This is clearly distinguishable from siblings like get-widget-guide, get-motion-guide, or get-ux-principle, and it also names the downstream companion tool review-illustration.

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 a concrete when-to-use clause ('when the user wants an illustration, diagram or explainer figure for docs, a blog post, a landing page or a launch') and an explicit entry sequence ('call with topic: isometric-concept first, or {} for the index'). It falls short of 5 because it never says when NOT to reach for this guide — e.g. when a sibling like get-three-js-guide or get-widget-guide is the better fit.

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