score_indexScores a complete set of 30 answers and returns the index (0–100), tier, per-dimension scores, strengths, and the signals holding the company back. Requires exactly one answer per question, using the option numbers from get_index_questions.
| Name | Required | Description | Default |
|---|---|---|---|
| answers | Yes | One entry per question id 1–30. | |
| company_website | No | The company's website, if you know it (optional) |
Changes observed during successful MCP inspections.
Input schema / properties / company_websiteAdded value: +{
+ "description": "The company's website, if you know it (optional)",
+ "maxLength": 300,
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare readOnlyHint=false, openWorldHint=false, idempotentHint=false; the description adds real context by spelling out the strict input contract (exactly 30 answers, one per id) and the shape of the computed result. It stops short of saying whether the score is persisted, echoed, or whether re-scoring is deterministic despite idempotentHint=false.
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?
Two sentences, front-loaded with the action and its output, followed by the input constraint. No filler or 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 no output schema, the description correctly compensates by listing the returned fields (index, tier, dimensions, strengths, blockers), and it also states the input requirement and its prerequisite sibling. An agent has everything needed 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% (ids 1–30, 1-based option numbers, min/max items all documented), so the schema already carries parameter meaning. The description's reminder about option numbers from get_index_questions is a useful cross-reference but largely restates the schema's own text, which is the baseline-3 case.
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?
States a specific verb and resource (scores a set of 30 answers) and enumerates exactly what comes back: index 0–100, tier, per-dimension scores, strengths, and limiting signals. It also names the sibling get_index_questions as the source of option numbering, so an agent can distinguish it from score_startup_idea without opening a schema.
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?
Gives a clear precondition (exactly one answer per question, option numbers taken from get_index_questions) and routes the agent to that sibling first. It does not, however, state when to prefer this tool over email_index_report or get_enhanced_index_report, so exclusions are absent.
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.