Pineprompt

List Prompt Analytics Tool

list-prompt-analytics-tool

Read-onlyIdempotent

Per-prompt aggregates (visibility, share-of-voice, sentiment, position) scoped to a single brand, plus the distinct tracked brands mentioned in each prompt's responses during the window. Paginated. To fetch more rows, request the next page; the envelope reports the total under meta.last_page.

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": {
      "project_id": "<project_id>",
      "brand_id": "<brand_id>",
      "start_date": "<start_date>",
      "end_date": "<end_date>"
    },
    "name": "list-prompt-analytics-tool"
  }
}

Input Schema

Name	Required	Description
`page`	No	1-indexed page number. Defaults to 1.
`tags`	No	Tag IDs (prompt classifiers) to limit responses by. Optional.
`sort_by`	No	Sort key. One of: visibility, share_of_voice, sentiment, position. Defaults to visibility.
`brand_id`	Yes	Numeric ID of the brand to scope per-prompt metrics to. Must belong to the project.
`end_date`	Yes	Inclusive UTC end of the analytics window. Must be on or after `start_date` and on or before today.
`interval`	No	Bucket granularity for time-series tools. One of: day, week, month, year. Required for time-series tools, ignored for aggregate tools.
`monitors`	No	Monitor IDs in the active project. Optional.
`per_page`	No	Page size, 1-100. Defaults to 25.
`segments`	No	Segment IDs (brand groupings) to slice analytics by. Optional.
`sort_dir`	No	asc or desc. Defaults to desc.
`countries`	No	ISO-3166-1 alpha-2 country codes to include. Optional.
`platforms`	No	AI platforms to include. Optional. Values: chatgpt, perplexity, gemini, grok, copilot, claude, google_ai_mode, google_ai_overview.
`project_id`	Yes	Project to compute analytics for.
`start_date`	Yes	Inclusive UTC start of the analytics window. ISO 8601 date (YYYY-MM-DD).

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 15, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so safety is covered. The description adds genuinely new behavioral detail: the response is paginated and the envelope exposes the total under `meta.last_page`, which an agent cannot learn from the annotations. It does not mention rate limits or result-size constraints, keeping it below a 5.

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?

Three tight sentences with the payload described first and the pagination mechanics last. Nothing is redundant and no filler appears. The one-word sentence 'Paginated.' is slightly clipped but earns its place as a flag.

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 a 14-parameter read-only analytics tool with no output schema, the description covers what comes back (aggregate metrics plus tracked brands), the scoping (single brand, window), and the pagination contract. The main gap is that it never explains how the filter parameters alter the result set, but that is largely handled by the fully described schema.

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 the schema already documents all 14 parameters including page, per_page, sort_by, and date bounds. The description reinforces only two of them implicitly ('scoped to a single brand', 'during the window') and says nothing about the filtering dimensions (tags, segments, platforms, countries, monitors) that materially change the output. Baseline 3 is appropriate.

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?

The description names the resource precisely (per-prompt aggregates) and enumerates the metrics returned (visibility, share-of-voice, sentiment, position), plus the secondary payload of distinct tracked brands mentioned in each prompt's responses. It is clearly distinguishable from prompt-CRUD siblings like get-prompt-tool or update-prompt-tool. It stops short of naming the analytics siblings (list-brand-analytics-tool, list-platform-analytics-tool) that an agent might confuse it with, so it lands at 4 rather than 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the brand-scoping and date-window language signals this is the per-prompt breakdown for one brand. The only explicit guidance is pagination ('to fetch more rows, request the next page'), which is about mechanics rather than tool selection. There is no statement of when to prefer this over list-brand-analytics-tool or list-source-url-prompt-analytics-tool.

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

All Pineprompt 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?