Mark

Save Claim

save_claim

Adds or revises a claim on the Claims & sources page. A claim is one fact drafts may state (a price, a result, a certification, a feature), backed by a quote that must appear in its source's text. Claims are append-only, so posts that cite a claim keep the wording they were approved against:

Add: text, category, sourceQuote, and either sourceId (list_claims or get_brand_context sources) or source {title, body, url?} to create the source too.
Revise: id of an active claim plus only the fields that change. This retires that claim and creates a new one; the result has the new claim and retiredId. Each call creates a claim. To stop drafts using a claim, call retire_claim. Only active claims reach Mark's drafting and post checks. Related: list_claims, retire_claim, add_source, get_brand_context.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "save_claim"
  }
}

Input Schema

Name	Required	Description
`id`	No	An active claim's id, to revise it. Omit to add.
`text`	No	The fact, in one sentence.
`source`	No	A new source to create and quote from, instead of sourceId. Nothing is saved if the quote is not in its body.
`category`	No	A short label grouping the claim, like Price or Customer results. Reuse a category list_claims already shows when one fits. Competitor pages read a competitor's prices from claims in the Price category.
`sourceId`	No	An existing source's id from list_claims.
`sourceQuote`	No	Words copied from the source's text that prove the claim.

Output Schema

Name	Required	Description
`mode`	Yes
`claim`	Yes
`appUrl`	Yes
`retiredId`	Yes	The claim that was retired, if any.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 4, 2026

changedInput schema / properties / category / description

Previous value: -"cert, price, lead_time or spec."New value: +"A short label grouping the claim, like Price or Customer results. Reuse a category list_claims already shows when one fits. Competitor pages read a competitor's prices from claims in the Price category."

removedInput schema / properties / category / enum

Removed value: -[
-  "cert",
-  "price",
-  "lead_time",
-  "spec"
-]

removedOutput schema / properties / claim / properties / category / enum

Removed value: -[
-  "cert",
-  "price",
-  "lead_time",
-  "spec"
-]

Changed4 schema fields changedOct 11, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

removedInput schema / properties / active

Removed value: -{
-  "const": false,
-  "description": "false, with id only, retires the claim.",
-  "type": "boolean"
-}

changedInput schema / properties / id / description

Previous value: -"An active claim's id, to revise or retire it. Omit to add."New value: +"An active claim's id, to revise it. Omit to add."

changedOutput schema / properties / mode / enum

Previous value: -[
-  "added",
-  "revised",
-  "retired"
-]New value: +[
+  "added",
+  "revised"
+]

AddedOct 8, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Goes well beyond the annotations: it discloses append-only semantics, that revision retires the old claim and creates a new one (returning new claim plus retiredId), that a quote not present in the source body means nothing is saved, and that only active claims feed drafting/post checks. These are consequential behavioral facts an annotation like destructiveHint=false cannot 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?

Front-loaded with purpose, then bulleted Add/Revise modes, then caveats — a structure that scans well. Slight redundancy ('Each call creates a claim' repeats what the Revise bullet already says) and the related-tools tail could be tighter, but nothing is filler.

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?

Covers the complex cases for a 6-param tool with nested objects: inline source creation, quote validation failure behavior, revision return shape, and the interaction with retire_claim and drafting. With an output schema present, it correctly does not spend words enumerating return fields.

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?

Schema coverage is 100% so the baseline is 3, but the description adds real meaning the schema cannot express: that sourceId and source are alternatives (either an existing source or one created inline), and which fields are needed for Add versus Revise. It does not clarify what happens when both are supplied or which fields are required on revise, which keeps it below a 5.

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 concrete verb+resource ('Adds or revises a claim on the Claims & sources page') and immediately defines what a claim is (a fact backed by a quote present in its source). It clearly distinguishes the two modes, add vs revise, and names the sibling tool (retire_claim) that handles the case this tool does not.

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?

Explicit routing: use Add when creating a claim with a quote, use Revise when passing an id of an active claim, and use retire_claim instead when the goal is to stop drafts from using a claim. It also lists related tools (list_claims, add_source, get_brand_context) so the agent knows where the required ids come from.

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

All Mark 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?