Skip to main content
Glama

AgentGid

by com.agentgid
OverviewDiscussionsAdmin

Plan a project from a tested kit

plan_project
Read-only

Get a project kit: one part per job from AgentGid's catalogs (with version, license and reasons), install lines, checks, and with files=true the AGENTS.md brief, CREDITS.md, first prompt and MCP setup files. Give a recipe id from list_recipes or the goal in plain words. If no recipe fits the goal, it says so and lists the recipes: it never improvises a stack.

Input Schema

NameRequiredDescriptionDefault
onNoSwitch parts on or off: {role id: true|false}. Optional parts start off. Assets, agent skills and MCP servers can be switched off, and the brief then says they were removed; parts the plan is built on (libraries, runtimes, services) can only be swapped through picks
addNoAdd up to 8 parts from AgentGid's catalogs that the recipe does not list: item ids such as "tool:pikepdf" or {"item": id, "stage": "agent|build|check|ship"}. They are checked against the answers like every part and marked as added in the files.
goalNoWhat to build, in plain words, e.g. 'a Mario-style browser game'
filesNoAlso return the texts of AGENTS.md, CREDITS.md, first-prompt.txt, install.txt and setup files
packsNoChoose a pack, model or font inside a picked source: {role id: item id}
picksNoSwap a part: {role id: item id}, ids as in a previous answer's parts[].pick and alternatives
promptNoFirst prompt: stop after each step (default) or run the whole plan
recipeNoRecipe id from list_recipes, e.g. 2d-platformer
answersNoAnswers by question id, e.g. {"use": "commercial", "budget": "free", "agent": "cursor", "style": "pixel"}

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / on / description
      Previous value: -"Switch parts on or off: {role id: true|false}. Optional parts start off; any part can be switched off, and the brief then says it was removed"New value: +"Switch parts on or off: {role id: true|false}. Optional parts start off. Assets, agent skills and MCP servers can be switched off, and the brief then says they were removed; parts the plan is built on (libraries, runtimes, services) can only be swapped through picks"
  2. Changed1 schema field changed
    • changedInput schema / properties / on / description
      Previous value: -"Switch optional parts on or off: {role id: true|false}"New value: +"Switch parts on or off: {role id: true|false}. Optional parts start off; any part can be switched off, and the brief then says it was removed"
  3. Changed1 schema field changed
    • addedInput schema / properties / add
      Added value: +{
+  "description": "Add up to 8 parts from AgentGid's catalogs that the recipe does not list: item ids such as \"tool:pikepdf\" or {\"item\": id, \"stage\": \"agent|build|check|ship\"}. They are checked against the answers like every part and marked as added in the files.",
+  "items": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "object"
+      }
+    ]
+  },
+  "type": "array"
+}
  4. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds real behavioral context beyond that: it never improvises a stack, it refuses and enumerates recipes on a miss, and it specifies the exact output composition including what files=true unlocks.

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?

Front-loaded with the primary outcome ('Get a project kit'), then progressively narrows to contents, input options, and fallback. Dense but every clause carries information; the single long opening sentence is the only mild readability cost.

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 9 documented parameters, no annotations gaps and no output schema, the description does the job of describing return contents (parts with version/license/reasons, install lines, checks, AGENTS.md/CREDITS.md/prompt/setup files). It stops short of noting pagination or size limits, but nothing essential to correct invocation is missing.

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 description coverage is 100%, so the baseline is 3 and the schema already carries the parameter burden. The description reinforces files=true and the recipe-vs-goal input path, but adds little syntax or meaning beyond what the schema's own property descriptions provide.

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 ('Get a project kit', one part per job), then enumerates exactly what a kit contains (versions, licenses, install lines, checks, optional files). It routes to the sibling list_recipes for recipe ids, so an agent can distinguish it from the find_* and list_* tools without opening a 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?

The description explicitly tells the agent how to seed the call — a recipe id from list_recipes or a plain-words goal — and names the sibling that supplies recipe ids. It also covers the failure path ('if no recipe fits the goal, it says so and lists the recipes'), but does not say when to prefer this over alternatives like find_tools or report_kit_issue.

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

All AgentGid toolsInspect
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources