Skip to main content
Glama

ILIT Society - directory of allergists offering intralymphatic immunotherapy

What the site does not do

what_the_site_does_not_do
Read-onlyIdempotent

The site’s limits, to state before acting for a person: it takes no bookings, gives no medical advice, holds no medical records, does not rank practitioners and sets no prices of its own; and ILIT is not FDA-approved, so in the US it is given off-label. Takes no input.

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": "what_the_site_does_not_do"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Output Schema

NameRequiredDescriptionDefault
does_notYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds some context on the nature of the content (limits and off-label caveat) but nothing beyond annotations about behavior — no note on whether the text is stable, versioned, or jurisdiction-specific. 'Takes no input' merely restates the empty schema.

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?

A single front-loaded sentence led by 'The site's limits' and structured as a semicolon-delimited enumeration, which is dense but appropriate for a list of disclaimers. Every clause is substantive payload rather than filler. The trailing 'Takes no input' is the one expendable fragment.

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?

An output schema exists and the parameter schema is empty, so the description carries no return-value or argument burden. For a static, argument-free reference tool, naming what the limits are is the essential information and it is supplied. Minor gap: it does not indicate whether the disclaimer text is jurisdiction-dependent beyond the US off-label note.

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?

The tool has zero parameters, so the baseline is 4 and there is nothing for the description to compensate for. 'Takes no input' is redundant with the empty object schema but harmless. No parameter meaning is missing because no parameters exist.

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 name alone is opaque, but the description enumerates exactly what the tool returns: the site's limits — no bookings, no medical advice, no records, no practitioner ranking, no own pricing — plus the off-label status of ILIT in the US. That is a concrete, specific resource rather than a restatement of the title. It does not, however, distinguish this from content-bearing siblings like get_facts, which could plausibly cover the same ground.

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 clause 'to state before acting for a person' implies a usage condition — surface these limits ahead of taking action on someone's behalf — which is a real, if terse, when-to-use signal. No alternatives are named and no when-not guidance is given, so an agent facing both this and get_facts has no explicit routing rule. Implied usage only.

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