lemon_references

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

With no annotations, the description carries the burden for behavioral disclosure. It correctly implies a read-only informational retrieval and no side effects, but it does not explicitly state safety, output format, or behavior when id is omitted. It adds minimal behavioral context beyond what the resource-oriented wording already suggests.

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 composed of two tightly written sentences that front-load the core content (award-winning sites and lessons) and then add a single, meaningful usage caveat. The example list is dense but purposeful, and there is no fluff or repetition of schema details.

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 simple reference tool with two optional parameters, the description gives a good sense of content, but it does not describe the return shape (e.g., array of objects with site and lesson fields) or how id and rubric affect the output. Since there is no output schema, a bit more explicit return-structure context would improve completeness.

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 input schema already provides 100% descriptive coverage for both id and rubric, so the baseline is 3. The description does not mention parameters at all, which is fine given high schema coverage, but it also does not reinforce or elaborate on parameter usage, so it stays at baseline.

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 clearly states the tool returns a curated set of 2025-26 award-winning sites each with one stealable lesson, and the phrase 'Taste compass, not clone list' further clarifies intent. It lacks an explicit verb like 'list' or 'get', but the resource and scope are unambiguous and distinguishable from siblings like palette or type_spec.

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 description implies the tool is used for design inspiration and taste guidance ('Taste compass'), but it does not explicitly state when to prefer this over siblings like lemon_trend_report or lemon_design_principles. No alternatives are named and no when-not conditions are provided, so usage must be inferred.

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