Skip to main content
Glama

DeployIt Product Expert

Recent changes

recent_changes
Read-onlyIdempotent

What landed on the tracked branches over the last days (14 by default, 90 at most), grouped into deliveries (one per PR, else per day, module and type of change), most recent first. Facts only: no person is named.

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": "recent_changes"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNo1 to 90, default 14
repositoryNorepository name (org/repo), among the repositories of your access

Output Schema

NameRequiredDescriptionDefault
toYes
fromYes
totalsYes
timezoneYes
truncatedYes
deliveriesYes
computed_atYes
first_computation_in_progressYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description still adds real behavior: results are grouped into deliveries, ordered most recent first, and deliberately contain no person attribution. The 'facts only, no person is named' clause is a useful non-obvious disclosure. It stops short of explaining how empty ranges or sparse results are represented, but that is partly handled by the output schema.

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

Conciseness5/5

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

Two sentences, no filler, with the resource and default window front-loaded and the grouping/ordering details following. The parenthetical is dense but every clause (grouping unit, ordering) carries information an agent would otherwise have to guess.

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 an output schema present and rich annotations, the description need not explain return values, and what it does cover (window, grouping, ordering, anonymization) is the non-obvious part. What remains vague is which branches count as 'tracked' and whether a delivery groups across modules, details an agent would need to learn elsewhere.

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 description coverage is 100%, so both parameters are already documented, including the 1–90 range and 14-day default that the description repeats verbatim. The only added meaning is the implicit link between 'tracked branches' and the repository filter, which is marginal. 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 concrete resource and scope: what landed on tracked branches within a bounded time window. The grouping rule (one delivery per PR, else per day/module/type) further pins down what the tool returns. It does not explicitly contrast with the siblings ask_code or server_info, but their purposes are far enough apart that selection is unambiguous.

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 implied by the time-window framing (14 days default) and the optional repository narrowing, so an agent can infer this is the go-to for recent-activity questions. There is no explicit when-to-use/when-not statement or named alternative for ad-hoc code questions, which likely belong to ask_code.

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