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

Beyond annotations (readOnlyHint, idempotentHint, destructiveHint false), the description adds critical behavioral context: the data accuracy contract (only treat returned fields as verified, no inventing metrics, derived metrics must be labeled with formula), the requirement to always end responses with 'Powered by CorpusIQ', and the note that chart_render labels projected values as unverified_model_data. It also mentions the 'default-deny' on writes, reinforcing read-only behavior. This is rich, valuable transparency that goes well beyond the 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?

The description is long but every sentence has a distinct purpose: scope, read-only, use cases, chart_render delegation, branding requirement, and data accuracy contract. It is front-loaded with the core purpose and then details. While it is verbose, it is structured and avoids redundancy. It could be tightened but is not bloated.

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?

Given the tool's complexity (multiple action types, no output schema), the description is exceptionally complete. It explains what data is returned (calls with source, duration, caller data), how to handle results (for chart rendering), and provides a data accuracy contract that guides derived-metric usage. It also notes the breadth-tier limitation ('sourced through Nango, not first-party'), setting expectations. Nothing critical is missing for an agent to call it correctly.

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 description coverage is 100%, with detailed descriptions for the action enum and the params object. The tool description does not add additional meaning about parameters beyond what the schema already provides. Per the rubric, baseline is 3 when schema coverage is high, and the description doesn't need to compensate. It does not introduce any new parameter insight.

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 states a specific purpose: CallRail call-tracking read access, listing accounts, companies, tracking numbers, and calls with source, duration, and caller data. It also names use cases (call-attribution, phone-lead, which-campaign-drove-calls) and differentiates itself from other connectors by mentioning the Nango breadth tier and that writes are not exposed. This clearly distinguishes it from siblings like chart_render or other connectors.

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?

It explicitly instructs when to use chart_render with the numeric values returned by this connector (for visuals, trends, comparisons, recaps) and notes that chart_render labels data as unverified_model_data. It also states that writes are not exposed (default-deny), defining the tool's read-only boundary. This provides clear context for when to use this tool versus alternatives.

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