Gemral Edge

Physical Infrastructure Footprint

get_physical_footprint

Physical-infrastructure footprint of one US-listed company: data-center build permits, power plant pipeline and regional grid load for the sites tied to the company, as publicly known on the as_of date. Renamed keys: eia_subba and hifld_lines_5km are deprecated aliases of grid_zone and transmission_lines_5km (same values, listed in deprecated_fields; old keys removed 2027-01-24). Counts (site_count, plant_count, event_count_365d) plus site and plant lists, newest first. capacity: permitted backup generator capacity in MW per site (an upper bound on onsite backup power, not IT load; lower_bound_sites counts sites where the figure is a floor because part of the permit is not yet itemised). trade_context: US imports of the goods tied to the company (by 6-digit HS code and country of origin), labelled sector_context_not_company: industry context, not the company's own revenue or purchases; about 11 tickers have no linked goods and return available=false. land_records: U.S. county land-use and building records (one county so far, starting 20 October 2026) for data-center land parcels held by the company's legal entities and the permitted data-center buildings on them (every original record field, permit number, issue date, floor area, build status, owner), plus planned data-center project areas within 300 m of its sites; each row is the version as first seen on or before as_of. Locations are as published; grid load is regional, not per site; fields not yet measured are null. Read-only evidence.

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": {
      "ticker": "<ticker>"
    },
    "name": "get_physical_footprint"
  }
}

Input Schema

Name	Required	Description
`as_of`	No	Optional date YYYY-MM-DD (default today): footprint as publicly known on that date
`limit`	No	Max sites / plants listed (counts always cover all)
`ticker`	Yes	Stock ticker, e.g. AMZN, MSFT, NEE

Output Schema

Name	Required	Description
`notice`	No	Free-tier upgrade notice; only when results are masked/delayed.
`results`	Yes	Tool result payload (read-only evidence). Shape varies by tool; scoring weights are never exposed.
`history_limit`	No	Present when the license limits history depth: earliest_allowed date, history_days and how many older items were removed.
`deprecated_fields`	No	Present only while a renamed key is still returned next to its replacement: field (old key), replacement (new key, same value), removal (ISO date after which the old key is gone).

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 26, 2026

addedOutput schema / properties / deprecated_fields

Added value: +{
+  "description": "Present only while a renamed key is still returned next to its replacement: field (old key), replacement (new key, same value), removal (ISO date after which the old key is gone).",
+  "items": {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  "type": "array"
+}

First observedOct 23, 2026

TDQS

B3.1/5.0

Behavior2/5

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

The description adds substantial real context beyond annotations: deprecated key aliases (eia_subba/hifld_lines_5km with a removal date), null semantics for unmeasured fields, capacity being an upper bound rather than IT load, and limited land-record coverage. However, it closes with 'Read-only evidence' while annotations declare readOnlyHint=false, a direct conflict that leaves an agent unsure whether the call mutates state.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is one very long run-on block mixing deprecation notices, field-by-field data definitions, and caveats, with little front-loading or sentence-level structure. Much of it restates individual output fields (site_count, plant_count, land_records columns) that an output schema already exists to convey.

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 data-retrieval tool with an output schema and annotations, the description covers the important caveats an agent needs: null for unmeasured fields, regional rather than per-site grid load, deprecated aliases, and coverage limits on land records. The remaining defect is the read-only conflict rather than missing information.

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 ticker, as_of, and limit are already fully documented including the limit default and that counts ignore limit. The description reinforces the as_of semantics ('as publicly known on that date') but adds no format or constraint details the schema doesn't already carry, so baseline 3 applies.

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 a specific resource set (data-center build permits, power plant pipeline, regional grid load) tied to one US-listed company, which no sibling tool covers. It is a noun phrase rather than a verb ('footprint of one US-listed company'), but the domain is unmistakable and clearly separate from signal/forecast siblings.

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?

Scope is implied (one company, US-listed, as publicly known on as_of), and one useful edge case is stated: ~11 tickers have no linked goods and return available=false. There is no explicit when-to-use/when-not guidance and no naming of alternatives or prerequisites (e.g. whether ticker must be US-listed, or what to use for non-US companies).

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

All Gemral Edge tools Inspect

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.