Read chat conversations in Dietbox. Actions: list (conversations, filter by patient/unread), messages (message history for patient).
[Flattened action: list]
Bulk support: accepts patient_ids for batched execution.
| Name | Required | Description | Default |
|---|---|---|---|
| take | No | ||
| unread | No | ||
| account | No | ||
| patient_id | No | ||
| patient_ids | No |
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?
Annotations already declare readOnlyHint, idempotentHint, and not destructive. The description adds valuable behavioral traits: bulk support via patient_ids and filtering by patient/unread. No contradictions with annotations.
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?
The description is short but includes redundant terms like '[Flattened action: list]' and mixes actions (list/messages) which could be clearer. It front-loads the purpose but could be more concise.
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?
With no output schema and 0% schema coverage, the description should explain return format and usage details. It mentions listing and messages but lacks output structure, pagination hints (take), and relationship to sibling chat tools. Incomplete for practical use.
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?
Schema has 0% description coverage. The description clarifies that 'patient_id' and 'unread' filter results, and 'patient_ids' enables batch execution, but 'take' and 'account' are unexplained. This leaves significant gaps for a 5-parameter tool.
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 'Read chat conversations' and lists actions (list, messages), clearly indicating it retrieves chat data. The tool name and sibling 'dietbox_chat_messages' help distinguish listing from messages, though the inclusion of both actions in the description creates slight ambiguity.
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 implies use for listing conversations or message history but does not explicitly differentiate from sibling 'dietbox_chat_messages' or provide when-not guidance. No alternatives are mentioned.
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.
Many tools have nearly identical descriptions, differing only by a single action name (e.g., dietbox_agenda_list vs dietbox_agenda_summary, multiple anamnesis read tools). This makes it hard for an agent to choose the correct tool. The splitting of CRUD operations into separate tools per action creates significant overlap.
Most Dietbox tools follow a consistent `dietbox_<entity>_<action>` snake_case pattern, but tools like `authenticate`, `connect`, `marketplace`, `report_bug`, `show_version`, and `toolkit_info` break this, making naming partially inconsistent. Overall, the pattern is clear for the core domain.
With 42 tools, the server is overburdened. Many tools are redundant due to splitting actions (e.g., three read tools for anamnesis), and non-domain tools (marketplace, bug reporting) inflate the count unnecessarily. A more streamlined set of 15-20 tools would be more appropriate.
The server covers a wide range of nutrition practice features: patients, appointments, anamnesis, anthropometry, chat, food diary, goals, finances, meal plans (read-only), prescriptions, and clinical records. However, notable write operations are missing (meal plans, goals, finance transactions), and some read-only tools lack corresponding edits.