Run an AI diagnosis on a B2B lead: digital maturity, opportunities and a recommended approach. This calls the LLM and costs tokens; not read-only. Admin only.
| Name | Required | Description | Default |
|---|---|---|---|
| leadId | Yes | The lead ID to diagnose |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes | The tool result rendered as human and AI readable text or markdown. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false), the description adds critical context: the tool costs tokens, is not read-only, and requires admin privileges. This transparency about cost and authorization goes well beyond structured fields, with no contradictions to 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 two sentences, front-loaded with the core purpose ('Run an AI diagnosis on a B2B lead: digital maturity, opportunities and a recommended approach') followed by essential behavioral notes. Every sentence earns its place with zero redundancy.
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?
With one simple parameter, high schema coverage, an existing output schema, and annotations, the description fully covers what an agent needs: purpose, output scope, cost implications, and authorization requirements. No gaps remain for this tool's complexity level.
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% with leadId described as 'The lead ID to diagnose'. The tool description does not add new parameter-level details beyond what the schema provides, so it meets the baseline of 3 without further enrichment.
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 clearly states the tool runs an AI diagnosis on a B2B lead, covering digital maturity, opportunities, and a recommended approach. It distinguishes itself from sibling tools like get_b2b_lead (retrieves lead data) and generate_b2b_pitch (generates a pitch) by specifying the action 'run' and the resource 'diagnosis'.
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 mentions that the tool calls the LLM, costs tokens, is not read-only, and is admin-only, which provides clear context for when to use it. However, it does not explicitly list when not to use it or compare to alternative siblings like get_b2b_lead for simple data retrieval, leaving some ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct function or data aspect, from idea CRUD to simulations, content generation, and team management. Despite the large number, descriptions clearly differentiate purposes, e.g., 'get_idea_summary' vs. 'get_idea_agents' vs. 'get_idea_evolution'. No two tools appear to do the same thing.
All tools follow a consistent verb_noun pattern in snake_case (e.g., 'create_idea', 'get_competitive_density', 'toggle_favorite'). No mixing of conventions like camelCase or abbreviations. The pattern is uniform and predictable.
63 tools is far beyond the typical well-scoped range of 3-15. While the platform's broad scope (idea validation, B2B, team, simulations) justifies many, the sheer volume can overwhelm an agent. A more curated subset or grouping would improve coherence.
The tool set covers the full startup idea lifecycle: creation, validation, retrieval of various analyses, updates, deletion, sharing, simulations, B2B lead generation, team collaboration, and market intelligence. No obvious gaps exist for the stated domain.
