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

Beyond the annotations (readOnlyHint, openWorldHint, idempotentHint), the description adds behavioral insights: 'Prefers higher-engagement listings' discloses a ranking preference, and 'Returns up to 5 picks with a one-line rationale each' explains the output structure. This extra context helps the agent understand what to expect beyond the safety guarantees already provided.

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 compact—two sentences plus a list of examples—yet packs essential information. The primary purpose is front-loaded, examples are illustrative without being verbose, and there is no redundancy with the schema or annotations.

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 recommendation tool with a clear schema and annotations, this description is complete. It covers the source ('live UK inventory'), the selection criteria ('budget and intent', 'higher-engagement listings'), the output format (up to 5 picks with rationale), and gives practical examples. The presence of an output schema means return values need not be detailed further.

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 80%, so the baseline is 3, but the description adds semantic value by showing how budget, intent, and category combine in examples. For instance, 'a road bike for £1,500 for weekend rides' implicitly maps to budgetGbp=1500, category=road, and useCase=weekend rides, which clarifies the intended usage of the free-text 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 description opens with 'Curated picks from Cyclesite's live UK inventory for a budget and intent,' clearly stating the action (curating picks) and resource (bikes from live inventory). It distinguishes itself from sibling search tools by emphasizing 'curated picks' and 'prefers higher-engagement listings,' which signals a recommendation engine rather than raw search.

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 provides three concrete example queries ('a road bike for £1,500 for weekend rides', 'best e-MTB I can buy under £3,000', 'commuter bike in London under £400'), which clearly illustrate the intended usage context and parameter combinations. However, it does not explicitly state when not to use this tool or mention alternative sibling tools, so it falls short of a 5.

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