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

Annotations already indicate this is a write operation (readOnlyHint=false). The description adds context about config structure and the stream type being 'fed by the ingest endpoint,' but it does not disclose potential side effects like external network calls or authentication requirements (e.g., DeepAPI) that are only mentioned in the schema, not the description. It provides some behavioral context beyond annotations, but not rich detail.

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 a single dense paragraph, but every segment is informative. It front-loads the action ('Create a lead source') then efficiently enumerates config types and scheduling. While it is not visually structured, it avoids fluff and packs essential information into a compact form. Slightly hard to parse due to density, but appropriately sized for the tool's complexity.

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?

The tool is complex: 7 parameters, nested objects, multiple type-dependent configs, and scheduling. The description covers the config variants, scheduling, and notes the stream type's special ingestion mechanism. It does not mention return values, but no output schema exists, so that is not a gap. Missing details like toolId references for tool_output and exact csv rows structure are minor given the overall 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 description coverage is only 14%, with most parameters lacking descriptions. The tool description compensates significantly by specifying the shape of `config` for each type (e.g., web_scrape {url|urls[]}) and the structure of `schedule` (cron {time,days?} / interval {everyMinutes} / once {runAt}). This adds critical semantic meaning beyond the bare schema. However, it does not define nested fields like `rows[]` or `args` fully, so it is not exhaustive.

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 begins with 'Create a lead source,' which is a specific verb plus resource, clearly indicating the tool's purpose. It further elaborates on multiple source types (text_paste, web_scrape, document, etc.), distinguishing it from sibling tools like neuron_list_lead_sources or neuron_run_lead_source. The purpose is unambiguous and well-scoped.

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 clear context on how to configure different source types and schedule options, e.g., 'Set scheduleKind cron/interval/once for recurring.' It implicitly says to use this tool when creating any kind of lead source. However, it does not explicitly name alternative tools or state when not to use it, so it lacks the explicit pointers seen in the highest benchmark examples.

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