Proofsource

Check my brand in AI answers

add_brand

Idempotent

Start measuring a brand: does ChatGPT, Perplexity, Claude or Google AI mention it, and who does AI recommend instead? Give the brand's website (or its app store, Google Maps, YouTube or Instagram link). It reads the site, picks the buyer questions, and starts the first scan across the AI engines. Reading the site takes 1-2 minutes; if it is still running, call again with the same link and it picks up the same run, never a second one. Returns the brand_id; then use get_scan_status.

Input Schema

Name	Required	Description
`link`	Yes	The brand's website, like acme.com, or its app store, Google Maps, YouTube or Instagram link.
`locations`	No	Optional: the cities or areas where the brand's buyers are, like ["Pune", "Indiranagar, Bengaluru"]. Its buyer questions are then split across them and its numbers shown per location. Leave out for a brand with one location.
`description`	No	Optional: what the brand sells, in a sentence. Only needed when add_brand says it couldn't read the website.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 30, 2026

addedInput schema / properties / locations

Added value: +{
+  "description": "Optional: the cities or areas where the brand's buyers are, like [\"Pune\", \"Indiranagar, Bengaluru\"]. Its buyer questions are then split across them and its numbers shown per location. Leave out for a brand with one location.",
+  "items": {
+    "maxLength": 120,
+    "type": "string"
+  },
+  "maxItems": 25,
+  "type": "array"
+}

First observedOct 13, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well beyond the annotations: it discloses the 1-2 minute site-reading latency and explains idempotency concretely ('call again with the same link and it picks up the same run, never a second one'), which makes idempotentHint=true actionable. It also states the return value (brand_id) and that the tool itself reads an external site, consistent with openWorldHint=true and readOnlyHint=false.

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?

Purpose is front-loaded in the first sentence and each subsequent sentence adds operational value (accepted link forms, execution time, retry semantics, next step). It is dense but slightly long, with the parenthetical link list and retry clause adding bulk that could be tightened.

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

Completeness5/5

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

For an async, side-effecting creation tool with no output schema, it covers everything an agent needs: what starts, how long it takes, how to poll without duplicating a run, what ID comes back, and which sibling to call next.

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 all three parameters are already documented with examples and constraints. The description reinforces the link variants and the 'description is only a fallback' condition, but adds no meaning the schema lacks, and it never mentions the locations parameter or its per-location splitting behavior.

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?

States a specific verb and resource ('Start measuring a brand') and immediately makes the output concrete: whether ChatGPT, Perplexity, Claude or Google AI mention it and who is recommended instead. It also distinguishes itself from siblings by naming get_scan_status as the follow-up and by accepting website or social/app-store links, so an agent can tell what this does versus list_brands or get_scan_status.

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 (you want to start tracking a brand) and explicitly routes the agent afterward to get_scan_status, plus tells it how to resume an in-flight run. It does not state when not to use it (e.g., brand already exists — presumably list_brands), so it falls short of full alternatives coverage.

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

All Proofsource tools Inspect

Try in Browser