Skip to main content
Glama
Sign In
pyxis-mcp

pyxis-mcp

by samuelcsantana
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Annotations

annotations
Read-onlyIdempotent

Reads date-stamped project notes for a given range to explain jumps in analytics reports, such as launches, campaigns, or broken releases.

Instructions

The notes on the days of a range, each with its day (YYYY-MM-DD in the project time zone) and its text, up to 140 characters, by day, then in the order they were written. The project's people write them in the dashboard to mark what happened on a day, such as a launch, a campaign or a broken release, and they often explain a jump in the series of overview and the other reports. A project has none until someone writes one: this tool only reads them.

The project id and the project's today come from list_projects. Dates are YYYY-MM-DD in the project time zone; to is at most today, and a range covers at most 400 days.

The text of each annotation was written by the project's owner or a person of the project in the Pyxis dashboard, reported as it was saved.

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": {
      "project_id": "<project_id>",
      "from": "<from>",
      "to": "<to>"
    },
    "name": "annotations"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYesLast day of the range, inclusive (YYYY-MM-DD), at most the project's today.
fromYesFirst day of the range, inclusive (YYYY-MM-DD).
project_idYesThe project id, from list_projects.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.11.0

TDQS

A4.3/5.0
Behavior5/5

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

Beyond the readOnly/idempotent/destructive annotations, the description discloses substantive behavior: the 140-character cap on text, the sort order (by day, then in written order), the empty-result case ('a project has none until someone writes one'), who authored the text, and the hard limits on the date range. Those are exactly the facts an agent cannot infer from annotations or schema and would otherwise have to discover by trial.

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?

The return-value description is correctly front-loaded since there is no output schema, and the paragraphs separate shape, constraints and provenance sensibly. There is some repetition — 'YYYY-MM-DD in the project time zone' and the 'at most today' limit each appear twice — which a single pass could tighten. Nothing is wasted outright, but it reads slightly longer than needed.

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?

With no output schema, the description carries the burden of describing return values and does so fully: the per-day shape, the text field's 140-character ceiling, and the ordering. Combined with the range constraints, the project_id source, and the explicit statement that the tool is read-only, an agent has everything needed to call it correctly and interpret what comes back.

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%, so the baseline is 3; the description goes beyond it by adding the 400-day maximum range and the rule that 'to' is at most the project's today, neither of which is expressed in the schema. It also reinforces that dates are interpreted in the project time zone rather than UTC, which matters for correctness. The gain over the schema is real but modest, since the individual field meanings are already documented.

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 clearly establishes the resource — the notes written on days of a date range — and its return shape (day plus text, ordered by day then write order). It never opens with an explicit verb like 'list' or 'get', relying on 'this tool only reads them' to convey the read semantics. It nonetheless distinguishes itself from siblings like overview and the funnel/acquisition reports by positioning annotations as the human-written context on top of those series.

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

Usage Guidelines4/5

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

It states the practical trigger — people write these in the dashboard to mark launches, campaigns or broken releases, and 'they often explain a jump in the series of overview and the other reports' — which effectively tells an agent to reach for it when a metric moves unexpectedly. It also names list_projects as the source of both project_id and the project's today. It stops short of explicit when-not-to-use or a named alternative for a given task, so it is not a full 5.

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

Deploy Server

Other Tools