Skip to main content
Glama

Filing lists and categories

manage_categories
Destructive

Look up how recipes are filed, or remove a legacy category. taxonomy: the allowed course/main/cuisine/diet/method/occasion values to use in save_recipe and update_recipe (read-only). list: the user's own app categories with recipe counts (read-only). unassign: remove categories from one recipe (write, new revision). Returns {taxonomy} | {categories:[{path, recipes}]} | {id, categories}.

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": {
      "action": "<action>"
    },
    "name": "manage_categories"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathsNounassign only: category paths to remove, e.g. ["Desserts > Pies"]
actionYestaxonomy, list, or unassign
recipe_idNounassign only: recipe id (UUID)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

The annotations already flag destructiveHint=true and non-idempotent, but the description adds the key non-annotation fact that unassign is '(write, new revision)' — i.e. the removal is captured as a revision, implying recoverability via restore_revision. The '(read-only)' tags on taxonomy and list clarify that two of three actions are safe reads despite the destructive annotation. It does not state permission requirements or whether unassign conflicts with concurrent edits.

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?

A single front-loaded sentence names the capabilities, then compact per-action clauses with the return shape last. Every clause earns its place; no filler or repetition of the schema verbatim.

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, the description usefully enumerates return shapes per action ({taxonomy}, {categories:[{path, recipes}]}, {id, categories}). The read/write and revision semantics are covered. Gaps: no error behavior for unknown paths, no note on whether removing a category not assigned to the recipe is a no-op, and no permission context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description's action annotations ('unassign only') merely restate what the schema descriptions already say about paths and recipe_id. No additional format details (e.g. path separator behavior, max paths, what happens with unknown paths) are supplied, so the schema carries the parameter weight.

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?

The description opens with the two core capabilities (look up filing, remove a legacy category) and then names the three actions with what each does: taxonomy values, user categories with counts, and unassign. An agent can tell exactly what the tool does and that it is multiplexed, though the opening sentence underrepresents the read-only taxonomy lookup relative to the enumerated actions.

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?

Each action carries a usage context: taxonomy is the value source 'to use in save_recipe and update_recipe', list is 'the user's own app categories', unassign is 'remove categories from one recipe'. This implicitly routes the agent away from writing via save_recipe/update_recipe when it only needs the allowed values. No explicit 'do not use this for X' exclusion, so it stops short of 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources