FeedSquad

Performance Insights

get_performance_insights

Read-onlyIdempotent

Engagement-ranked performance over a recent window: top performers, underperformers, and an LLM-generated summary of what worked and one candidate angle to try next. Reads stored post performance (post_performance) and matches it to FeedSquad posts by platform_post_id, so MCP-created and campaign-created posts are both covered. PRIVACY: when include_summary is true (default), post text and aggregate engagement metrics are sent to FeedSquad's configured LLM provider for summarisation; include_summary=false returns only the structured metrics. Each row carries its post_id.

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": "get_performance_insights"
  }
}

Input Schema

Name	Required	Description
`top_n`	No	Top + bottom performers to return (default 5, max 10).
`platform`	No	A single platform to report on.
`lookback_days`	No	Days to consider (default 30, max 180).
`include_summary`	No	When true (default), the result includes an LLM summary.

Output Schema

Name	Required	Description	Default
`kind`	Yes
`summary`	No
`platform`	Yes
`sample_size`	Yes
`lookback_days`	Yes
`top_performers`	Yes
`underperformers`	Yes
`suggested_next_angle`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 6, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the readOnly/idempotent annotations, the description adds important behavior: it identifies the stored performance source, explains how posts are matched via platform_post_id, and discloses that include_summary sends post text and aggregate metrics to an external LLM provider. That privacy and data-flow disclosure is exactly the kind of context an agent needs before invoking the tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core return shape and then adds the data-source and privacy details in compact, high-value sentences. Every sentence contributes useful information and the PRIVACY callout is easy to locate.

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?

Given the output schema and annotations, the description supplies the remaining context an agent needs: what is returned, where the data comes from, how posts are matched, and the privacy trade-off of the summary option. No material behavioral gap remains.

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 parameters are already documented. The description still adds meaningful semantics by explaining the external-LLM privacy consequence of include_summary and by noting that each returned row carries post_id, which helps downstream use.

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 states a specific resource and operation: engagement-ranked post performance over a recent window, returning top and bottom performers plus an LLM summary. It also explains the underlying data source (post_performance matched by platform_post_id), which clearly separates it from sibling tools like get_post or search_posts.

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?

The description makes the tool's reporting purpose clear, but it does not explicitly say when to use this tool versus alternatives such as get_post, search_posts, or get_usage. Usage is implied by the performance-insight framing rather than stated with exclusions or routing guidance.

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

All FeedSquad 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?