Skip to main content
Glama
Sign In

invisit

by dev.invisit
OverviewDiscussionsAdmin

AI assistants

get_ai_assistants
Read-onlyIdempotent

What each AI operator does with a site: visits its assistants sent, live fetches while answering someone, and reads by its search and training crawlers, plus the pages assistants fetch and which of them got no visits. Visits work on every site; the crawler columns need the server connected. Assistant fetches are a floor: assistants also answer from their own index, so a page can get more visits than fetches, and visits over fetches is not a click-through rate.

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": {
      "site_id": "<site_id>"
    },
    "name": "get_ai_assistants"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoLast day, inclusive, YYYY-MM-DD; default today
fromNoFirst day, YYYY-MM-DD; overrides period
periodNoWindow ending now; days are whole days in the timezone. Ignored when from is set.30d
site_idYessite_id from list_sites; a site name, slug or domain also resolves
timezoneNoIANA zone for day boundaries; default the user's

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-open-world, so the safety profile is covered. The description goes beyond them with genuinely non-obvious data semantics: partial column availability when the server is not connected, and the caveat that assistant fetches are a floor because assistants also answer from their own index, so visits-over-fetches is not a click-through rate. Return format and pagination are not described, costing it the top score.

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?

Two sentences, front-loaded with what the tool reports and closed with the interpretation caveat, with essentially no filler. The first sentence is a long dense enumeration that takes a second pass to parse, and the opening 'what each AI operator does with a site' delays the concrete content, which is the main structural weakness.

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 five fully documented parameters and no output schema, the description carries the burden of explaining what comes back, and it does by listing the visit, live-fetch and crawler columns plus pages with no visits. It also flags data-availability limits and a misinterpretation risk that an agent would otherwise get wrong. Only the response shape and ordering are left unstated.

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 coverage is 100%, so site_id, from, to, period and timezone are all documented in the schema, establishing the baseline of 3. The description adds no parameter-level meaning: it never mentions that from overrides period, how day boundaries interact with timezone, or which window the metric comparison uses. It neither helps nor contradicts 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 description names the resource (AI assistant traffic to a site) and enumerates the specific measures: assistant visits, live fetches while answering, and search/training crawler reads, plus fetched pages with no visits. The opening clause 'What each AI operator does with a site' is fuzzy on its own but is immediately unpacked into concrete metrics. It never names a sibling tool, so the boundary with get_breakdown or get_overview is left implicit.

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?

Usage is only implied by the metric list; there is no 'use this instead of X when Y' routing despite a large sibling set that includes generic breakdown/overview tools. What it does offer is a real prerequisite: visits work on every site, while crawler columns require the server to be connected. That is a useful selection condition, but the when-not-to-use case is absent.

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

All invisit 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