Namequota

Score brand share in AI answers

score_answer_share

Read-onlyIdempotent

It never queries an AI engine: if the answers are not pasted, ask for them and their source links first. Call this when a user pastes answers from ChatGPT, Perplexity, Google AI Mode, Claude or another AI assistant and asks whether they named or linked their brand, what share they got, which rivals or sites were chosen instead, or what to do about it. Pass the brand, its domain, rival names and every answer in answers (each with its prompt, engine and source links). Returns mention share and citation share (such as 0 of 3) by engine and for buyer prompts (prompts that do not name the brand), how often each rival is named, the sites cited instead and a short fix list. A repeated prompt is not a mention, and a link counts only if it goes to the brand domain.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "brand": "Acme CRM",
      "links": [
        "https://acme.com/pricing",
        "https://www.g2.com/categories/crm"
      ],
      "answer": "For a small team, Acme CRM is simple. HubSpot is a common pick too.",
      "domain": "acme.com",
      "prompt": "best CRM for a small sales team"
    },
    "name": "score_answer_share"
  }
}

Input Schema

Name	Required	Description
`brand`	Yes	The brand or product name to look for, such as Acme CRM.
`links`	No	The source links the engine showed with the answer. URLs written in the answer text are read too.
`answer`	No	One answer to score. Use answers instead for several prompts.
`domain`	No	The brand's website, such as acme.com. A link to it counts as a citation. An apex domain counts its subdomains.
`engine`	No	Which engine gave the answer, such as chatgpt, openai-web-search, perplexity, google-ai-mode, claude. Used to split the share by engine.
`prompt`	No	The question that was asked. Its words are removed from the answer before matching, so an engine that repeats the question does not count as naming you.
`aliases`	No	Other names that count as the brand, such as Acme or AcmeCRM.
`answers`	No	Several answers to score together (at most 50), for a share across prompts and engines.
`competitors`	No	Rivals to count in the same answers, each with a name and optionally a domain.

Output Schema

Name	Required	Description	Default
`all`	Yes
`brand`	Yes
`buyer`	Yes
`domain`	Yes
`method`	Yes
`answers`	Yes
`summary`	Yes
`by_engine`	Yes
`next_step`	Yes
`competitors`	Yes
`top_sources`	Yes
`recommendations`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 23, 2026
- changedInput schema / properties / aliases / items / maxLength
```
Previous value: -100New value: +200
```
- changedInput schema / properties / brand / maxLength
```
Previous value: -100New value: +200
```
- changedInput schema / properties / competitors / items / properties / name / maxLength
```
Previous value: -100New value: +200
```
First observedOct 16, 2026

TDQS

A4.3/5.0

Behavior4/5

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

The annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. Beyond that, the description discloses the domain-specific counting rules that would otherwise be invisible: a repeated prompt is not a mention (prompt words are stripped), and a link counts only if it resolves to the brand domain. It also summarizes the output composition (mention share, citation share by engine and buyer prompt, rival frequency, sites cited, fix list), which is more than the annotations convey.

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?

The most important constraint ('never queries an AI engine') is front-loaded, and the sentence order moves logically from limitation, to trigger, to inputs, to outputs, to counting rules. It is dense but not padded, though the opening pronoun 'It' is a slightly weak anchor and the output enumeration in the middle sentence is long enough to compress.

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?

The tool is non-trivial - nine parameters, one required, with a batch 'answers' array and competitor objects - and the description covers the essential contract: what to supply, what it computes, and the two counting rules that determine correctness. Because an output schema exists, the return-value summary is a bonus rather than a gap; only the answer-versus-answers choice and alias handling remain underspecified.

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

Parameters3/5

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

Schema description coverage is 100%, so the baseline is 3. The description does add light grouping guidance - 'Pass the brand, its domain, rival names and every answer in answers (each with its prompt, engine and source links)' - which implicitly distinguishes the single-answer and batch paths, but it does not explain when to prefer 'answer' over 'answers', how aliases interact with matching, or what 'buyer prompts' implies for structuring the input.

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

Purpose5/5

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

The description gives a specific verb and resource ('score brand share' over pasted AI answers) and enumerates the exact questions it answers: whether the brand was named or linked, what share it got, which rivals or sites were chosen, and what to do. It also states up front what it is not ('never queries an AI engine'), which no sibling tool ('create_tracker', 'add_round') overlaps with, so an agent can route unambiguously.

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

Usage Guidelines5/5

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

Trigger conditions are explicit and concrete: 'Call this when a user pastes answers from ChatGPT, Perplexity, Google AI Mode, Claude or another AI assistant' and asks one of four listed question types. It also handles the negative case with a fallback action - if answers are not pasted, ask for them and their source links first - which prevents the agent from invoking prematurely or fabricating inputs.

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

All Namequota 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.