run_prospect_loop

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

No annotations are provided, so the description carries the full burden. It discloses the core behavioral traits: it enriches with live market signals, auto-drafts outreach, inserts scored leads into CRM, and degrades gracefully when Serper key is absent. This goes beyond a simple statement and outlines the sequence of actions. However, it does not mention potential side effects beyond CRM insertion, such as duplicate creation, idempotency, or rate limits, but the main behaviors are transparent.

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 two sentences, with the core purpose front-loaded. It packs a lot of information efficiently, but the first sentence is a long run-on that could be segmented for readability. There is no wasted verbiage, and the degradation note is useful as a separate second sentence. Overall, it is concise and structured reasonably well.

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 a complex, multi-step operation that mutates CRM data, yet there is no output schema and no annotations. The description explains the process and the degradation, but it does not mention what the tool returns (e.g., list of created leads, scores), whether it is a long-running operation, or any error conditions. For a tool of this complexity with zero structured context beyond the input schema, the description is incomplete in explaining the outcome and potential issues.

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 67%, so the schema already documents two of three parameters. The description adds context about the overall workflow (niche and market usage) but does not add specific syntax or format details for any parameter, and it does not explain the 'limit' parameter, which lacks a schema description. The description marginally reinforces the meaning of niche_query and market_query but does not compensate for the missing limit documentation.

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: 'Signal-driven prospecting' with a clear workflow (discover, enrich, auto-draft, insert) and references a distinct 'JoeCRM pattern'. It clearly distinguishes itself from sibling tools like crm_create_lead or collect_signals by describing a multi-step end-to-end process, not a single operation. The verb 'run' and the resource 'prospect_loop' are explicit, and the description explains what the tool does without being tautological.

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 usage for comprehensive prospecting with signal enrichment, and notes a fallback behavior when Serper key is absent. However, it does not explicitly state when to use this tool over alternatives (e.g., using crm_create_lead directly, or collect_signals alone), nor does it mention any exclusions or prerequisites such as CRM configuration or API keys beyond Serper. The guidance is inferred rather than explicit.

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