Skip to main content
Glama

Local MCP

by com.local-mcp
OverviewDiscussionsAdmin

Create Referral Invites

create_referral_invites
Destructive

Records referral invites for the colleagues a user chose to invite and returns a unique referral link per person, so the user can later see who installed or activated LMCP. It does not send anything itself — each returned link can be included in an email or message to that person. lang records the language the invite is written in (e.g. "es", "en").

Input Schema

NameRequiredDescriptionDefault
langNoISO language of the invite you're writing (the user's conversation language, e.g. 'es', 'en'). Defaults to the Mac's language.
confirmNoIgnored; kept for older clients.
recipientsYesThe picked recipients.

Output Schema

NameRequiredDescriptionDefault
nextNo
invitesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / confirm / description
      Previous value: -"Must be true to record the invites. Without it the call returns a preview and records nothing."New value: +"Ignored; kept for older clients."
  2. Changed1 schema field changed
    • addedInput schema / properties / confirm
      Added value: +{
+  "description": "Must be true to record the invites. Without it the call returns a preview and records nothing.",
+  "type": "boolean"
+}
  3. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations declare destructiveHint=true and openWorldHint=true, so the description's clarification that nothing is sent externally meaningfully narrows what openWorld ties actually occur. It also discloses the return shape (one unique link per recipient) and the side effect (records are persisted for later attribution). It does not address the destructiveHint flag or whether repeat calls create duplicate invites, so it is strong but not complete.

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?

The core action and return value are front-loaded in the first clause, and the non-sending caveat follows immediately where an agent needs it. The trailing `lang` sentence is somewhat redundant with the schema and could be dropped without loss.

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?

With an output schema present and annotations covering the safety profile, the description covers the essentials: what is persisted, that nothing is dispatched, and what comes back. The notable remaining gap is idempotency -- whether re-inviting the same person creates a second record or reissues the same link -- which matters for a write tool an agent may retry.

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 all three parameters (including the vestigial 'confirm', marked as ignored) are already documented. The description's gloss on `lang` ('records the language the invite is written in') largely restates the schema, though it does tie the value to the actual invite text, adding mild interpretive value. Baseline 3 applies.

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 ('Records referral invites') plus the concrete payload ('a unique referral link per person') and the downstream purpose ('see who installed or activated LMCP'). An agent can distinguish this from list_referral_candidates purely on this text -- one lists candidates, this one records invites and mints links.

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 usefully clarifies what the tool does NOT do ('It does not send anything itself'), which steers the agent away from expecting delivery. But it never states when to call this versus list_referral_candidates, nor any prerequisite (e.g. recipients must first be picked from the candidate list). Usage is implied rather than specified.

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

All Local MCP 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