mister-parc-mcp

À faire, en détail

parc_a_faire

Read-onlyIdempotent

Retrieve the dashboard's to-do list, filtered by severity or rubric, to identify affected repositories, pull requests to review, and library upgrades requiring action.

Instructions

La liste « À faire » du tableau de bord, avec le détail de chaque rubrique : dépôts concernés, PR à relire, montées de librairies (paquet, cible, dépôts et versions).

C'est la liste que la page affiche, calculée par le relevé ; rien n'est recalculé ici. Niveaux, du plus urgent au moins urgent : critique, attention, decision, entretien.

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": "parc_a_faire"
  }
}

Input Schema

Name	Required	Description	Default
`niveau`	No	Ne garder qu'un niveau de gravité.
`rubrique`	No	Ne garder qu'une rubrique, par sa clé : rouges, prs, correctifs…

Output Schema

Name	Required	Description
`page`	Yes
`items`	Yes
`genere`	Yes	Date du relevé qui fonde la réponse (ISO 8601).

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Oct 31, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/openWorld, and the description adds meaningful context beyond them: the data is the precomputed scan output, nothing is recalculated here, and results are ordered by severity. It doesn't discuss pagination or staleness of the underlying relevé, but the source-of-truth disclosure is valuable.

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?

Three short sentences, front-loaded with what the tool returns, followed by the source-of-truth note and the level ordering. No filler; minor redundancy between the title and first sentence.

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?

An output schema exists and params are fully documented, so the description needn't explain return shape; it covers the remaining gaps (origin of data, sort order, filter vocabulary). Slightly incomplete on whether the list reflects a cached/snapshot scan at call time.

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 both filters are documented in the schema; the description still adds value by spelling out the four severity levels and their ordering (« du plus urgent au moins urgent ») and by giving rubrique key examples (rouges, prs, correctifs). That goes beyond the raw enum values.

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?

States concretely that it returns the dashboard « À faire » list with per-section detail (repos, PRs to review, library upgrades with package/target/versions), which is a specific resource with enumerable contents. It doesn't name a sibling to contrast with, but the 'liste agrégée de la page' framing lets an agent tell it apart from the granular parc_prs/parc_renovate tools.

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?

The sentence « C'est la liste que la page affiche, calculée par le relevé ; rien n'est recalculé ici » implies when to pick it (to mirror the dashboard) versus tools that recompute, but no alternative is named explicitly and there are no exclusions. Usage is implied rather than prescribed.

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