Skip to main content
Glama
Sign In
Bevel MCP

Bevel MCP

by JoshPopov
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Log a food in Bevel

bevel_log_food

Logs a selected food to the Bevel Nutrition log by date and time, building the app's exact entry; use dryRun to preview before writing.

Instructions

Logs a food (from bevel_search_food) to the Nutrition log, building the exact entry the app sends. Bevel files a log into breakfast/lunch/dinner by its time; there is no separate meal field. Requires BEVEL_ENABLE_WRITES=true unless dryRun is set.

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": {
      "fdbId": "<fdbId>"
    },
    "name": "bevel_log_food"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNoDay YYYY-MM-DD in the configured time zone. Defaults to today.
timeNoLocal time HH:MM. Defaults to now (or the current time of day on `date`).
fdbIdYesfdbId from bevel_search_food.
queryNoThe search query that found it (used to re-fetch the food if needed).
dryRunNoIf true, return the entry that would be sent without sending it.
servingsNoNumber of servings (default 1).
servingIdNoservingId from the search result. Defaults to the food's default serving.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare non-read-only, non-destructive, non-idempotent, open-world. The description adds genuinely non-obvious behavior: meal slot is derived from the time field with no separate meal parameter, and it builds the exact payload the app sends. It stops short of warning about duplicate logging (relevant given idempotentHint=false) or describing error modes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with the core action, followed by the non-obvious meal-filing rule and the write-flag prerequisite. Nothing is padded or repeated from the schema.

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?

For a 7-parameter write tool with no output schema, the definition covers source, prerequisites, timing semantics, and the dryRun return behavior. Remaining gaps (duplicate handling, failure behavior, what a successful log returns) are modest rather than blocking.

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 baseline is 3, but the description adds meaning the schema lacks: the date/time pair silently determines breakfast/lunch/dinner, and dryRun returns the would-be entry rather than sending it. That explains parameter interaction rather than restating field docs.

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?

States a specific verb and resource ("Logs a food ... to the Nutrition log") plus the input source (from bevel_search_food), which cleanly separates it from the search, update, and delete siblings. An agent can tell what this does without opening the schema.

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?

Gives clear preconditions: the food must come from bevel_search_food via fdbId, and writes require BEVEL_ENABLE_WRITES=true unless dryRun is set. It does not explicitly route to bevel_update_food_log for modifying an existing entry, but the create-vs-modify split is strongly implied by "Logs a food".

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