MentionAgent

How often runs happen and what they do alone

set_run_settings

DestructiveIdempotent

Change the run schedule and automation. 'frequency' is one of three_times_daily, twice_daily, daily. 'preferredHour' is the UTC hour (0-23) a run should start from; -1 clears it. 'autoFollowup' turns automatic follow-ups on sites that went quiet on or off. 'autoSend' true means new batches are SENT WITHOUT REVIEW; confirm with the person before turning it on. Turning it off is always allowed. A site not yet eligible (warmup not done, or no batch approved by hand yet) keeps the request and switches on when it becomes eligible. 'minDr' and 'maxDr' limit new prospects to that Ahrefs Domain Rating range (1-84, 0 clears); smaller sites say yes more often, so a high minimum means fewer drafts. 'siteTopic' is a comma-separated list of fields a site AS A WHOLE must mainly be about (its homepage is checked), e.g. "real estate, home staging, interior design"; sites about something else are skipped even when one article matches. "" turns it off. It means fewer drafts, all on topic; get_campaign shows a suggestion. Pass only the fields to change.

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": {
      "workspaceId": "<workspaceId>"
    },
    "name": "set_run_settings"
  }
}

Input Schema

Name	Required	Description
`maxDr`	No	Skip prospects above this Ahrefs DR (1-84), or 0 for no maximum.
`minDr`	No	Skip prospects below this Ahrefs DR (1-84), or 0 for no minimum.
`autoSend`	No	Send batches without review. Confirm before true.
`frequency`	No	How often discovery and drafting run.
`siteTopic`	No	Fields a whole site must be about, comma-separated, up to 300 characters, or "" to turn the filter off.
`workspaceId`	Yes	Which site to act on. Call get_status with no arguments to list them.
`autoFollowup`	No	Automatic follow-ups on or off.
`preferredHour`	No	UTC hour 0-23, or -1 for no preference.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 14, 2026

addedInput schema / properties / maxDr

Added value: +{
+  "description": "Skip prospects above this Ahrefs DR (1-84), or 0 for no maximum.",
+  "type": "integer"
+}

addedInput schema / properties / minDr

Added value: +{
+  "description": "Skip prospects below this Ahrefs DR (1-84), or 0 for no minimum.",
+  "type": "integer"
+}

addedInput schema / properties / siteTopic

Added value: +{
+  "description": "Fields a whole site must be about, comma-separated, up to 300 characters, or \"\" to turn the filter off.",
+  "type": "string"
+}

First observedOct 2, 2026

TDQS

A4.2/5.0

Behavior5/5

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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description goes well beyond them: autoSend bypasses human review entirely, disabling it is always safe, and ineligible sites retain the request and apply it later. Those are exactly the consequences an agent cannot infer from annotations or schema.

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 and the dangerous autoSend warning are front-loaded, and every sentence conveys a distinct rule or tradeoff. It is long and reads as a field-by-field walkthrough, with a bit of duplication against the schema descriptions, but there is no filler.

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?

For an 8-parameter mutation with no output schema, it covers all settings, the risky one, eligibility deferral, and the partial-update contract. It does not say what the tool returns or how failures surface, which is the main remaining gap given there is no output schema.

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 earns more by explaining consequences rather than types: minDr/maxDr shift draft volume ('a high minimum means fewer drafts'), siteTopic is judged against the homepage and skips off-topic sites even when an article matches, and the sentinel values (-1, 0, "") are spelled out. Some overlap with schema text remains, but the decision-relevant nuance is new.

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?

Opens with a specific verb+resource ('Change the run schedule and automation') and then enumerates exactly which settings are in scope, which implicitly separates it from siblings like set_sending, set_warmup, and set_email_settings. It never names those siblings explicitly, so an agent must infer the boundary rather than being told it.

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 clear operating context: confirm before enabling autoSend, turning it off is always allowed, deferred activation when a site is not yet eligible, and 'Pass only the fields to change'. It also points at get_campaign for a topic suggestion. What it lacks is an explicit statement of when to reach for this tool versus set_sending/set_warmup.

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

All MentionAgent 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.