Movahedi Privacy API

Classify a cookie by who receives its data

classify_cookie

Read-onlyIdempotent

Classify one cookie by name: which vendor pattern it matches, the organisation that receives and uses the data (the legal party), its purpose, typical retention, and control class. Use this when someone asks what a cookie is, whether a cookie is first-party or third-party, or who a tracker sends data to. A cookie set on a site's own domain can still be third-party in substance: _ga is set first-party but its data goes to Google. Unknown names return known: false instead of a guess. Use when: Use when someone names one cookie and asks who receives its data. Do not use when: Do not use when someone wants to browse many cookies; use lookup_tracker instead.

Input Schema

Name	Required	Description	Default
`name`	Yes	The cookie name only, for example '_ga' or '_fbp'. Not a value, not a URL.

Output Schema

Name	Required	Description	Default
`classification`	Yes	The classification result for the cookie name.
`corpus_version`	Yes	Semantic version of the movahedi.ca statutory corpus this answer was drawn from, for example v2026.12.0. Pin it when citing; when it changes, re-read the affected resources and the change log at https://movahedi.ca/changelog/.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 4, 2026

addedOutput schema / properties / corpus_version

Added value: +{
+  "description": "Semantic version of the movahedi.ca statutory corpus this answer was drawn from, for example v2026.12.0. Pin it when citing; when it changes, re-read the affected resources and the change log at https://movahedi.ca/changelog/.",
+  "examples": [
+    "v2026.12.0"
+  ],
+  "type": "string"
+}

changedOutput schema / required

Previous value: -[
-  "classification"
-]New value: +[
+  "classification",
+  "corpus_version"
+]

AddedOct 21, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, and the description does not contradict them. Beyond that it discloses the most decision-relevant behavior for an agent: unknown names return known: false rather than a guess, and first-party placement does not imply first-party data flow. It does not describe coverage limits of the underlying vendor database, which is the remaining behavioral gap.

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 definition is well front-loaded: substance first, then the nuanced first/third-party example, then explicit use/do-not-use blocks. The only waste is mild redundancy between the opening sentence's 'Use this when someone asks...' and the later 'Use when:' line, which restate the same trigger.

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?

An output schema exists, so return fields need not be explained, and the description still previews them usefully; annotations cover the safety profile. Combined with the unknown-name fallback behavior, an agent has what it needs to call and trust the result. The one omission is how broad the vendor pattern coverage is, which affects when to distrust a known: false.

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 coverage is 100% and the only parameter is documented with examples and a 'not a value, not a URL' clarification, so the schema already carries the semantics. The description adds only marginal framing (name-only identification, max one cookie) beyond that. Baseline 3 is appropriate when the schema does the heavy lifting.

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 names a specific verb and resource ('classify one cookie by name') and enumerates exactly what the classification returns: vendor pattern, receiving legal party, purpose, retention, control class. It also explicitly distinguishes the case an agent would find confusing (first-party set, third-party in substance, using _ga as the example), which separates it from a generic lookup.

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?

It gives an explicit 'Use when' with a concrete triggering question (who receives this cookie's data) and an explicit 'Do not use when' that routes to a named sibling, lookup_tracker, for browsing many cookies. The alternatives and the condition selecting them are stated, not inferred.

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

All Movahedi Privacy API 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?