Tap

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

Annotations declare readOnlyHint=true and openWorldHint=true. Description adds valuable behavioral context: return format ({rows, events[], hasChanges}), event types (added/removed/changed), stateless nature, and specific monitoring scenarios. No contradictions with 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?

Information-dense with zero waste. Structure flows logically: operation definition → return format → event details → stateless workflow instructions → use cases. Every sentence conveys distinct value.

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?

No output schema exists, but description compensates effectively by detailing return structure and event types. Covers the 5-parameter complexity and nested object handling adequately. Could mention pagination or rate limiting for perfect 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?

Schema coverage is 100%, establishing baseline 3. Description adds crucial semantic workflow context for previousRows parameter (omit to establish baseline vs. pass to detect changes) and implicitly clarifies the tap identification pattern via site+name. Elevates beyond schema definitions.

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?

Description uses specific verbs ('Run a tap', 'diff against previous rows') and clearly distinguishes from sibling tap_run by emphasizing change detection and monitoring use cases. The return structure and event types are explicitly specified.

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?

Provides explicit workflow guidance for the two-phase usage pattern ('first call: omit previousRows to get baseline. Subsequent calls: pass previous rows'). Includes use case examples (price changes, new listings). Lacks explicit naming of tap_run as the non-diff alternative.

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