FeedSquad

List AI Tells

list_ai_tells

Read-onlyIdempotent

Lists the AI Tells Index, a public catalogue of patterns that signal low-effort writing. Optional filters: category, status, severity, detection, platform, language. Returns one summary line per entry with its id and url. The full record for an id carries the examples, the detection rule, the false-positive notes, and the sources. Every tell is a probabilistic signal, never proof of AI authorship: human writers trip these patterns too, and the false-positive notes say who. Public reference data. No user data is read and nothing is written.

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": "list_ai_tells"
  }
}

Input Schema

Name	Required	Description
`status`	No	Signal status to list. active still signals; fading is weakening; burned has collapsed as a signal but is kept because retired signal is information; contested is disputed.
`category`	No	One taxonomy category to list.
`language`	No	BCP-47 tag. The v1 dataset is English only.
`platform`	No	Lists only entries carrying a note about this platform.
`severity`	No	How strongly the pattern reads as low-effort.
`detection`	No	How the tell is detected: deterministic (regex), statistical (a measured metric), or judge (an LLM rubric).

Output Schema

Name	Required	Description	Default
`kind`	Yes
`count`	Yes
`tells`	Yes
`license`	Yes
`dataset_version`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 6, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the bar is lower. The description does add genuine context beyond them: the crucial caveat that tells are probabilistic signals and never proof of authorship, plus a pointer to false-positive notes. The closing 'no user data is read and nothing is written' partly restates the annotations, which keeps it from 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?

Front-loaded with purpose, then filters, then return shape, then a caveat — a logical order with no wasted sentences. The final 'Public reference data. No user data is read and nothing is written.' slightly duplicates the annotation profile rather than adding new information.

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?

With an output schema present, return values need no full explanation, yet the description still gives the shape of one summary line per entry with id and url. Filters, the summary-vs-detail split, and the interpretive caveat together cover everything an agent needs to call it correctly.

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% with detailed enum value explanations for status, category, platform, severity, and detection, so the description need not re-document them. It only restates the filter list ('category, status, severity, detection, platform, language'), adding no semantics beyond the schema, which matches the baseline 3.

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 specific verb and resource ('Lists the AI Tells Index, a public catalogue of patterns that signal low-effort writing') and immediately contrasts the summary listing with the full record retrievable by id, which implicitly separates it from the get_ai_tell sibling. An agent knows exactly what this tool returns without opening the schema.

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?

Explains the optional filters and signals that this is a summary-level listing whose detail lives behind an id (the get_ai_tell path), giving clear context for when to call it. It stops short of explicitly naming a when-not-to-use condition or the alternative tool by name.

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?