Skip to main content
Glama

agentswitchboard

Recommend

recommend
Read-onlyIdempotent

One recommendation for what your user needs, and the next step to start using it, as the site's Operator (/operator) picks it. Pass the need in a sentence you write yourself, e.g. "query Postgres and send email": each need it names gets one pick, why it fits, the next step (the MCP client config to paste when the vendor's docs give one, else its setup guide or docs) and two alternatives; two or more picks also come with a /stack link. Name a product to prefer the listings that mention it; say MCP, CLI, API, browser extension or official to narrow the pick. Picked by fixed matching rules, not a model, so the same need always gets the same answer. A need that matches no task is refused with the closest tasks. Never include names, email addresses or phone numbers.

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": {
      "need": "<need>"
    },
    "name": "recommend"
  }
}

Input Schema

NameRequiredDescriptionDefault
needYesWhat the user needs, in a sentence or two, e.g. "query Postgres and send email" (up to 300 characters are read)

Output Schema

NameRequiredDescriptionDefault
basisYesHow the pick is made
notesYes
answerYesThe recommendations in plain sentences, one line per need, ready to tell the user
requestYesThe need as read
stackUrlYesTwo or more picks as a shared stack on the site
unmatchedYesNeeds with no pick, and the tasks closest to them
operatorUrlYesThe same request on the site
recommendationsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedOutput schema / properties / recommendations / items / properties / alternatives / items / properties / lastChecked
      Added value: +{
      +  "$ref": "#/properties/recommendations/items/properties/pick/properties/lastChecked"
      +}
    • changedOutput schema / properties / recommendations / items / properties / alternatives / items / required
      Previous value: -[
      -  "name",
      -  "slug",
      -  "url",
      -  "iconUrl",
      -  "description",
      -  "provider",
      -  "categories",
      -  "accessMethods",
      -  "verified",
      -  "official",
      -  "authType"
      -]New value: +[
      +  "name",
      +  "slug",
      +  "url",
      +  "iconUrl",
      +  "description",
      +  "provider",
      +  "categories",
      +  "accessMethods",
      +  "verified",
      +  "official",
      +  "authType",
      +  "lastChecked"
      +]
    • addedOutput schema / properties / recommendations / items / properties / limitations
      Added value: +{
      +  "description": "What may stop or slow the user, read from the listing: the sign-in it needs, a server that runs only on their computer, no MCP config to copy yet, no MCP server, not Verified. Empty when the listing shows none",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / recommendations / items / properties / pick / properties / lastChecked
      Added value: +{
      +  "description": "YYYY-MM-DD the Verified listing was last checked (its link and access path), from its last update; null when it is not Verified",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • changedOutput schema / properties / recommendations / items / properties / pick / required
      Previous value: -[
      -  "name",
      -  "slug",
      -  "url",
      -  "iconUrl",
      -  "description",
      -  "provider",
      -  "categories",
      -  "accessMethods",
      -  "verified",
      -  "official",
      -  "authType"
      -]New value: +[
      +  "name",
      +  "slug",
      +  "url",
      +  "iconUrl",
      +  "description",
      +  "provider",
      +  "categories",
      +  "accessMethods",
      +  "verified",
      +  "official",
      +  "authType",
      +  "lastChecked"
      +]
    • changedOutput schema / properties / recommendations / items / required
      Previous value: -[
      -  "need",
      -  "task",
      -  "pick",
      -  "pickedBecause",
      -  "why",
      -  "unmet",
      -  "nextStep",
      -  "alternatives",
      -  "fits"
      -]New value: +[
      +  "need",
      +  "task",
      +  "pick",
      +  "pickedBecause",
      +  "why",
      +  "unmet",
      +  "nextStep",
      +  "limitations",
      +  "alternatives",
      +  "fits"
      +]
  2. Added

TDQS

A4.4/5.0
Behavior5/5

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

Adds real behavior beyond the annotations: the pick is deterministic ('fixed matching rules, not a model, so the same need always gets the same answer'), the output bundle includes a fit rationale, a next step and two alternatives plus a /stack link for multi-pick needs, and there is a hard privacy constraint ('Never include names, email addresses or phone numbers'). None of that is recoverable from the readOnly/idempotent/closed-world hints.

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

Conciseness3/5

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

Front-loaded with the core action, but the body is a single dense run-on chain of semicolon-separated clauses mixing output shape, input shaping, matching mechanics, refusal behavior and privacy rules. Every clause earns its place, but the packing makes it slower to parse than it needs to be.

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 one-parameter, read-only tool with an output schema, this covers input shaping, determinism, refusal, and privacy. The only gap is that 'the site's Operator (/operator)' is left as unexplained jargon, so an agent doesn't know what that entity is beyond 'picks the recommendation'.

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 baseline is 3, but the description earns an extra point by telling the agent what to put into `need` — a self-authored sentence, a concrete example, optional product names, and taxonomy keywords (MCP/CLI/API/extension/official) that steer the match. That is meaning the schema does not carry.

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 — 'One recommendation for what your user needs, and the next step to start using it' — plus the mechanism ('as the site's Operator picks it'). That separates it from siblings like search_agents (browse a catalog) and alternatives_to (swap one tool for others), which an agent can tell apart without opening any 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?

Gives clear conditions for shaping the call: 'Pass the need in a sentence you write yourself', 'Name a product to prefer the listings that mention it', 'say MCP, CLI, API, browser extension or official to narrow the pick'. It also explains a failure mode ('A need that matches no task is refused with the closest tasks'). It never says when to pick this over search_agents, so it stops short of a 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.