PointRover

Changes Since

pointrover_changes_since

Read-only

Returns what moved since an earlier answer: newly published figures upstream of the business, and recalls, storms or trade actions that opened, changed or ended. Use this when the assistant is coming back after a few days or checking whether a new tariff landed. Not for the business's own books: invoices, bank, payroll or accounting live in its accounting connector, not here. Nor is it pointrover_brief: this is what moved since a version, not the whole state. Pass since (string): a board_version from an earlier answer or a check id from pointrover_events; a bare number is answered with the field to pass, board_version. Example: pointrover_changes_since({"since": "v_20260901T032313Z_5087037f5922"}). Versions are kept 8 days; about 700 tokens at most.

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": {
      "since": "<since>"
    },
    "name": "pointrover_changes_since"
  }
}

Input Schema

Name	Required	Description	Default
`since`	Yes	A board_version from an earlier answer, or a check id from pointrover_events. A bare number is answered with the field to pass instead.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 4, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only declare readOnlyHint, so the description carries the rest and does it well: retention window ("versions are kept 8 days") defines the useful lookback and the failure mode for older ids, and the token ceiling hints at response size. It also discloses error behavior for a bare number plus the corrective field, which is genuinely non-obvious.

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: purpose first, then usage, then exclusions, then parameter guidance and an example. Nearly every sentence earns its place, though the since-handling explanation appears in both the narrative and the schema description, a small redundancy.

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 a one-parameter read tool with no output schema, this covers what is needed to invoke it: what it returns conceptually, the accepted input forms, the retention limit, and the sibling it replaces. The only untold detail, exact response shape, is fairly signposted by the token 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?

Schema coverage is 100% and the schema text already covers both accepted id kinds, so the description mostly restates it. It still adds value with a concrete example value showing the board_version format and by repeating the bare-number recovery path, but that overlaps the schema rather than extending it.

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?

"Returns what moved since an earlier answer" names a specific verb (returns) and a precise scope (delta since a given version), and immediately enumerates the resource classes covered: new upstream figures, recalls, storms, trade actions. It explicitly separates itself from pointrover_brief by stating this is movement since a version rather than the whole state.

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 concrete trigger conditions ("coming back after a few days", "checking whether a new tariff landed") and an explicit exclusion: invoices, bank, payroll and accounting are not here but in the accounting connector. It also preempts the adjacent sibling, pointrover_brief, so the agent knows which of the two to pick.

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

All PointRover 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.