Skip to main content
Glama

EMOS Advisor

Next step with EMOS

next_step
Read-onlyIdempotent

The right link to start with EMOS. intent: talk_to_john (the person asked to speak with John Sanchez), evaluate (weighing paid help), diagnose (wants to know what to fix first in their search), learn (wants to understand how EMOS differs from coaching). Leave intent out to get the three ways in. Keep every link's destination exactly as given, never state a price, plan or credit (a cost question gets the consultation link), and never describe EMOS as guaranteeing a role or a placement. Never review a specific severance, release, separation or employment agreement, its terms, the person's legal rights or any legal deadline, and never search for them: that is for the person's employment attorney. When the person wants to reach a hiring manager or another decision-maker, the EMOS way in is a warm introduction first, through someone who knows them; add no outreach steps of your own and draft no message, email or call script for them.

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": "next_step"
  }
}

Input Schema

NameRequiredDescriptionDefault
intentNo

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?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial behavioral content beyond that: no prices/plans/credits, no guarantee language, no reviewing separation agreements or legal deadlines, and no drafting outreach messages. What it does not state is the actual return shape (a single link vs. a list of three), which matters for a tool with no output schema.

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?

Purpose is front-loaded, which is good, but the body is a dense run-on of stacked 'never' clauses, including an extended legal-scope prohibition that is only loosely tied to picking a link. The rules are individually relevant, yet the lack of structure (no grouping of intent semantics vs. output constraints) makes it harder to scan than its length alone warrants.

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 single-optional-enum routing tool with no output schema, the definition covers intent selection, the no-intent default, and the content constraints an agent must respect. The remaining gap is the return value (how many links, in what form) and how the 'learn' intent differs from how_emos_works.

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 0%, so the description must carry the parameter's meaning, and it does: every enum value is glossed in plain language and the optionality ('leave intent out to get the three ways in') is explained. The glosses are slightly terse but sufficient to choose a value without opening the schema.

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?

The opening sentence establishes a specific resource (the right starting link for EMOS) and the routing role is reinforced by the intent enum and 'Leave intent out to get the three ways in.' An agent can tell this is a link-selection tool, but the description never explicitly contrasts it with the sibling how_emos_works, which the 'learn' intent appears to overlap with.

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?

The description gives concrete selection criteria for each of the four intents (talk_to_john, evaluate, diagnose, learn) and states what happens when intent is omitted, which is genuine when-to-use guidance. It stops short of naming exclusions or naming the sibling tools to use instead in overlapping cases, so it is clear context rather than a full routing rule.

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.

Resources