Skip to main content
Glama
Sign In

PatrolTech

by online.patroltech
OverviewDiscussionsAdmin

Access logs

patroltech_access_list_logs
Read-onlyIdempotent

Use when you want to know who has entered or is currently inside, from access control. Returns the entry and exit totals and the 20 most recent records (local time of the account, type, person, zone and location); with insideOnly: true, who entered and has not left. Never repeat the identity document of a visitor. Do not use when you need guard scans.

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": "patroltech_access_list_logs"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoEnd date of the range (inclusive), YYYY-MM-DD.
fromNoStart date of the range, YYYY-MM-DD (never words like "yesterday").
typeNoOnly entries or only exits. Omit it for both.
zoneNoAccess zone, written as in the dashboard. Omit it for all.
periodNoPeriod. Omit it (and from/to) for the last 24 hours.
locationNoLocation name. Omit it for all.
insideOnlyNotrue: only who is inside now (entries without an exit in the last 24 h; older ones come apart, as exits not recorded).
organizationNoOmit unless the account has more than one organization; then the exact name (or id) as listed by patroltech_account_get_context.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already cover read-only/idempotent/non-destructive safety, so the description goes beyond them usefully: it discloses the return payload (entry/exit totals plus the 20 most recent records and their fields), account-local time, a data-quality caveat that older 'inside' entries may show as unrecorded exits, and a PII handling rule ('Never repeat the identity document of a visitor'). Those are the kinds of traits an agent cannot infer from structured fields.

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?

Front-loaded with the use case and the return shape, then constraints; no filler sentences. It is dense — a long parenthetical field list and semicolon-chained clauses — which slightly hurts scannability but every clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-optional-parameter, no-output-schema read tool, the description supplies what the schema cannot: what comes back (totals plus capped recent records), the time basis, the insideOnly edge case, and the PII constraint. Nothing needed to invoke or interpret results correctly is missing.

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% and every parameter already carries a description, defaults included (omit period/from/to for last 24 h), so the schema does the heavy lifting. The description only reinforces insideOnly and never touches date-range vs. period interaction. Baseline 3 is appropriate.

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+resource (access-control entry/exit log) and the exact question it answers — 'who has entered or is currently inside'. It also disambiguates from a plausible sibling domain by saying 'Do not use when you need guard scans', so an agent can separate it from patroltech_scans_list_recent without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit positive trigger, an explicit anti-trigger ('guard scans'), and the condition that flips behavior ('with `insideOnly: true`'). The only minor gap is that the excluded sibling is named by domain rather than tool name, which is still unambiguous given the sibling list.

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

All PatrolTech 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