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

Beyond the annotations (read-only, idempotent, non-destructive), the description reveals the ranking mechanism, the fallback when embeddings are unavailable, and the one-result-per-site deduplication. It does not state the output shape, but no output schema exists and the safety profile is already covered by annotations.

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?

A single 25-word sentence packs the core behavior, criteria, fallback, and dedup rule with no filler or front-loading issues.

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 5-parameter read-only tool, the description covers the essential selection/ranking facts and the schema documents the more complex parameter semantics. It is missing any explicit 'when to use vs alternatives' guidance and an indication of result structure, but an agent can still invoke it correctly from the slug and limit params alone.

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 description's only parameter-related signal is 'One result per site,' which slightly clarifies the sameSite default, but it does not explain slug, limit, detail, or maxTokens beyond the schema. With schema coverage at 60% and the remaining params self-explanatory (slug/limit), a 3 is fair.

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 phrasing 'A screen's nearest design neighbours' names the exact resource (screens) and operation (find similar/neighbours), and the ranking criteria ('design-similarity embeddings... else by macrostructure / industry / style overlap') remove ambiguity about what 'similar' means. This distinguishes it from adjacent siblings like find_by_color or find_components without needing to inspect their schemas.

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 for retrieving similar screens from a starting screen, but it does not explicitly state when to use it over compare, recommend, or search_screens, nor any exclusions. The only indirect guidance is 'One result per site,' which hints at deduplication behavior rather than routing.

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