Skip to main content
Glama
Sign In

FeedSquad

by com.feedsquad
OverviewDiscussionsAdmin

Suggest Brand Memory Items for Review

propose_stash_items

Stages a batch of up to 30 pre-classified knowledge items stated or confirmed by the user in the current conversation into the user's FeedSquad brain (Stash). Each item names its section and field_path, so no classification runs and the wording is kept exactly. Every item requires evidence (why it is believed), which the user sees during review. Items land as PENDING in the Stash inbox; nothing is saved as fact until the user approves it.

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": {
      "items": "<items>"
    },
    "name": "propose_stash_items"
  }
}

Input Schema

NameRequiredDescriptionDefault
itemsYesUp to 30 pre-classified proposed items.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing that items land as PENDING in the Stash inbox and that nothing is saved as fact until user approval, and that evidence is shown to the reviewer. It does not address what happens on duplicate calls, despite idempotentHint=false.

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?

Four sentences, each carrying distinct information, with the batch limit, the no-classification guarantee, the evidence requirement, and the PENDING outcome all stated up front. Nothing is 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?

Complete enough for a single-object-parameter mutation with no output schema: it covers the batch cap, the required evidence, and the review gate. The remaining gap is what the call returns (item ids, counts) and duplicate-call behavior when idempotentHint is false.

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 already 100%, but the description adds real meaning: section/field_path are pre-classified so wording is preserved verbatim, and evidence is mandatory and user-visible. It still leaves the confidence field and the trailing-[] array-append convention unmentioned.

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: staging a batch of up to 30 pre-classified knowledge items into the user's brain (Stash). The clause 'pre-classified ... so no classification runs' implicitly separates it from tell_stash, but it never names that sibling explicitly, so an agent must infer the boundary.

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?

Provides context that items must be 'stated or confirmed by the user in the current conversation', which implies the right moment to call it. However, it never states when NOT to use it versus tell_stash, nor whether it should be called repeatedly as new facts surface.

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

All FeedSquad 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