Skip to main content
Glama

Mentionry

by com.mentionry
OverviewDiscussionsAdmin

Read latest answer reviews

read_latest_answer_reviews
Read-onlyIdempotent

Latest saved answer executions needing an owned-brand attribution review, with engine, recorded region/date, actual competing brands, excerpt, citations and a source-grounded review task. Last seven days; at most 200 question/engine/region/persona groups scanned per brand. Up to 30 pending and 30 reviewed/unchanged runs with triage state/version. triage.unchangedSinceReview references a prior explicit review of complete identical evidence; the current run remains reviewed=false. Use triage.needsReview for fresh tasks; changed or unverified earlier reviews need rechecking; state changes use dedicated review/restore tools. No comparison, provider calls or publication.

Input Schema

NameRequiredDescriptionDefault
daysNo
limitNo
offsetNo
workspaceNoOwned active workspace ID within this key’s scope; omit for its selected brand.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • removedInput schema / properties / area
      Removed value: -{
-  "enum": [
-    "SEO",
-    "GEO",
-    "both"
-  ],
-  "type": "string"
-}
    • changedInput schema / properties / days / default
      Previous value: -30New value: +7
    • changedInput schema / properties / days / maximum
      Previous value: -90New value: +7
    • removedInput schema / properties / direction
      Removed value: -{
-  "enum": [
-    "in",
-    "out",
-    "both"
-  ],
-  "type": "string"
-}
    • removedInput schema / properties / url
      Removed value: -{
-  "description": "Exact URL in the saved map; required for page/keywords/connections.",
-  "type": "string"
-}
    • changedInput schema / properties / workspace / description
      Previous value: -"Owned active workspace ID; omit for main brand."New value: +"Owned active workspace ID within this key’s scope; omit for its selected brand."
  2. Added

TDQS

A3.9/5.0
Behavior5/5

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

Goes well beyond the annotations (which already declare read-only/idempotent) by disclosing the seven-day window, the 200 question/engine/region/persona group scan cap per brand, and the 30 pending / 30 reviewed item cap. It also explains the non-obvious semantics of triage.unchangedSinceReview and why the current run stays reviewed=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?

Claims and limits are front-loaded in the first sentence and the follow-up fragments each carry distinct constraints with little filler. Structure is telegraphic (subject-less fragments like 'Last seven days; at most 200 ... groups scanned per brand'), which costs some readability but no sentence is wasted.

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?

With no output schema, the description does the work of listing returned fields and triage state/version, plus the scan and item caps, which is enough to call it correctly. Pagination/total-count behavior for offset/limit is the main omission.

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

Parameters2/5

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

Schema description coverage is only 25% (only workspace is documented), so the description should compensate for days, limit and offset, and it does not – the limit/offset pagination behavior and the interaction between the 1-7 `days` range and the stated 'last seven days' are unaddressed. The stated caps (30 pending/30 reviewed) also don't map cleanly onto the limit default of 25 with a max of 100.

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?

States a specific verb and resource: latest saved answer executions needing owned-brand attribution review, and enumerates what each item carries (engine, region/date, competing brands, excerpt, citations, review task). An agent can distinguish this read from review_answer_evidence/restore_answer_evidence, though those siblings are only referenced generically as 'dedicated review/restore tools'.

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?

Explicitly directs the agent to triage.needsReview for fresh tasks, flags that changed or unverified prior reviews need rechecking, and states that state changes belong to the dedicated review/restore tools rather than here. It also excludes comparison, provider calls and publication. Clear context and exclusions, only the sibling names themselves are left implicit.

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

All Mentionry toolsInspect
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