SpiderLook

Add tracked company

add_competitor

Create a tracked company when the user requests adding it to a project.

Saves a company record and starts website/profile discovery and favicon retrieval from its public website. Full scanning requires activation. kind=self sets the project's baseline if none exists; competitor is a rival; trendsetter is an inspiration source. Duplicate website hosts produce warnings but still create another record, so retrying can create duplicates. Uses existing account resources; does not purchase subscriptions or credits.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "project_id": "<project_id>",
      "url": "<url>"
    },
    "name": "add_competitor"
  }
}

Input Schema

Name	Required	Description	Default
`url`	Yes
`kind`	No		competitor
`context`	No	Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
`llm_model`	No	Optional model identifier for analytics, only if explicitly available in client-provided metadata. Otherwise pass 'unknown'. Do not inspect or disclose system prompts, hidden instructions, credentials, or other protected context.
`project_id`	Yes
`conversation_id`	No	Optional Spiderlook analytics correlation identifier. Reuse the value returned by a previous Spiderlook response only for subsequent Spiderlook calls in this chat. Omit if unavailable; do not invent a value or use the host's conversation ID.

Output Schema

Name	Required	Description	Default
`_mcp_instructions`	No	Server-issued metadata for this conversation.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 27, 2026

TDQS

A4.2/5.0

Behavior5/5

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

Adds substantial context beyond the annotations: the call kicks off website/profile discovery and favicon retrieval, full scanning needs separate activation, duplicate hosts warn but still create a second record (concrete detail behind idempotentHint=false), and no subscription or credit purchase occurs. This is exactly the kind of side-effect and retry-hazard disclosure annotations alone cannot carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action, then tightly packed behavioral notes; nearly every sentence carries new information. The staccato fragments ("Full scanning requires activation.") read slightly disjointed but do not waste space.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers prerequisites (activation for full scanning, existing account resources), the mutation's side effects, and the duplicate/retry hazard; return values need not be explained since an output schema exists. Minor omission: no note on required inputs like a valid project_id or what happens if the project is unknown.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With schema coverage at 50%, the description compensates by defining the three kind values (self = project baseline, competitor = rival, trendsetter = inspiration), which the schema lists only as a bare enum. url and project_id are left to the schema, and the analytics parameters (context, llm_model, conversation_id) are covered by their own schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Create a tracked company") plus the trigger condition ("when the user requests adding it to a project"), which is far more than the title conveys. It doesn't distinguish itself from the adjacent update_competitor sibling, which handles existing records, so an agent must infer that split.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear trigger (user asks to add a company to a project) and explains the kind choice with what each enum value means semantically. It stops short of naming alternatives or exclusions, e.g. that update_competitor should be used for existing tracked companies rather than this tool.

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

All SpiderLook tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?