feedback_gebenGibt Rueckmeldung zur Plattform selbst weiter — was nicht funktioniert, was fehlt, was stoert. Landet bei den Betreibern. Nutze das, wenn dein Nutzer sich ueber die Plattform beschwert oder sich etwas wuenscht, statt es nur zu bestaetigen.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Die Rueckmeldung, in den Worten des Nutzers |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no informative annotations (readOnlyHint=false, destructiveHint=false, etc.), the description carries the behavioral burden. It discloses that feedback 'Landet bei den Betreibern' (goes to operators), which is a useful behavioral trait. However, it doesn't mention side effects, confirmation, or anything about reversibility — acceptable for a simple feedback tool but not rich disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two compact sentences with no fluff. The first sentence front-loads the action and scope; the second provides usage guidance. Every phrase earns its place, and the message is immediately parseable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter tool with no output schema and nested objects, the description covers purpose, scope, destination, and usage conditions. It doesn't specify return values, but that's unnecessary here. The only small gap is not explicitly describing the tool as a write-action with potential side effects, but annotations already signal non-read-only.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema covers the single parameter text 100%, including 'in den Worten des Nutzers'. The description adds some context by listing example feedback content (what doesn't work, what's missing, what bothers), but it largely restates the schema's intent. Baseline 3 is appropriate since the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific action ('Gibt Rueckmeldung ... weiter') and a clear resource ('zur Plattform selbst'), distinguishing it from sibling tools like post_melden. It defines the scope with concrete examples (was nicht funktioniert, was fehlt, was stoert), so an agent immediately understands what this tool is for.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives an explicit usage condition: 'Nutze das, wenn dein Nutzer sich ueber die Plattform beschwert oder sich etwas wuenscht' — this clearly tells the agent when to select this tool. It does not explicitly name alternatives or when not to use it, but the platform-scope wording implicitly separates it from post reporting and other actions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Tools target distinct resources: marketplace entries, chats, own posts, profiles, notifications, and reporting. There is mild overlap between benachrichtigungen, chats_ansehen, and meine_treffer, but the descriptions give clear usage guidance.
Most tools follow a German object_verb pattern like markt_ansehen, post_erstellen, or profil_aendern. Deviations like benachrichtigungen and meine_posts are readable but break the otherwise consistent pattern.
15 tools is at the upper end of the ideal range, but the marketplace scope legitimately covers browsing, posting, messaging, profiles, notifications, and moderation. Each tool has a real place, though a few could be conceptually merged.
Core lifecycles are covered: posts can be created, viewed, closed, reactivated, and deleted; chats can be listed, read, sent to, and managed; profiles can be viewed and updated. Minor gaps remain, such as no way to edit an existing post or manage notifications individually.