Skip to main content
Glama
bLd75

rundata · La Réunion 974 en direct

by bLd75
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Donner un avis à rundata.re

donner_avis

Send feedback to rundata.re about missing data, incorrect or stale values, suggestions, or thanks when a search lacks results or returns wrong information.

Instructions

Transmet à rundata.re, qui tient ce serveur, un avis sur ses données : une donnée qui manque (« manque »), une valeur qui semble fausse ou périmée (« erreur »), une idée (« suggestion »), ou un remerciement (« bravo »). L'appeler sans attendre qu'on le demande quand un outil n'a pas trouvé ce que l'utilisateur cherchait, a renvoyé quelque chose de faux ou d'incomplet, ou quand l'utilisateur exprime un souhait ou une plainte sur ces données, ou dit après coup qu'une information de rundata.re était fausse : c'est ainsi que le service s'améliore. Écrire un message court et concret (quel outil, quel lieu, ce qui manquait). Ne mettre aucune donnée personnelle ; si le contenu touche la personne (son adresse, sa santé…), lui demander d'abord son accord. Les avis sont lus par une personne, sans réponse directe. / Send feedback to rundata.re: missing data, a wrong value, a suggestion or thanks. Use it when a tool lacked data or erred, or the user voiced a wish or complaint; no personal data.

Input Schema

NameRequiredDescriptionDefault
lieuNoLe lieu concerné (« Cilaos », « plage de l'Hermitage »). / The place concerned.
typeYes« manque » (donnée absente), « erreur » (valeur fausse ou périmée), « suggestion », « bravo ». / missing, wrong, suggestion, praise.
outilNoL'outil concerné (« meteo_actuelle », « transports »…). / The tool concerned.
messageYesL'avis, en quelques phrases (1000 caractères au plus), sans donnée personnelle. / The feedback, no personal data.
question_utilisateurNoLa question de l'utilisateur, reformulée sans rien de personnel. / The user's question, paraphrased, nothing personal.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.128.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations declare a non-read-only, non-destructive, non-idempotent mutation; the description adds genuinely behavioral facts beyond that: feedback is read by a human, there is no direct reply, and personal data must be excluded (with a consent step for content touching the person). It doesn't discuss repetition/duplicate behavior despite idempotentHint=false, which keeps it off a 5.

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?

Purpose is front-loaded, then usage triggers, then content constraints — a sensible order. It is somewhat long because every point is duplicated in French and English, but each sentence earns its place; no filler.

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 no output schema, a bilingual enum schema, and explicit annotations, the description covers purpose, triggers, privacy rules, and the no-reply expectation. Minor gaps remain (e.g., whether the call should be confirmed with the user before sending, or what 'lieu'/'outil' should contain when unknown), but nothing essential for correct invocation is missing.

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 schema already defines all five fields and the enum. The description still adds value by prescribing how to fill 'message' (short, concrete: which tool, which place, what was missing) and by reinforcing the no-personal-data constraint that binds the message and question_utilisateur fields.

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?

The description states a specific action (transmet un avis à rundata.re) and enumerates the four feedback categories with quoted enum values, so the agent knows exactly what the tool produces. It is unmistakably distinct from every sibling, which are all read-oriented data tools.

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?

Explicit triggers are given: call it when a tool lacked data, returned something wrong or incomplete, or when the user voices a wish, complaint, or later says info was false — and explicitly without waiting to be asked. This is strong when-to-use guidance with a proactive instruction.

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