Skip to main content
Glama

codex_projects

Destructive

List, select, or create Codex project directories by absolute path, with pagination using offset and limit.

Instructions

List selected projects with offset/limit; select/create takes path. The main agent chooses an absolute project directory.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "codex_projects"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoAbsolute directory to select/create
limitNo
actionNolist
offsetNo

Output Schema

NameRequiredDescriptionDefault
okYes
result_versionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.3

TDQS

B3.3/5.0
Behavior2/5

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

Annotations declare destructiveHint=true, readOnlyHint=false, idempotentHint=false and openWorldHint=true, so the safety burden is partly carried. The description, however, adds no behavioral detail about what 'select' actually does (does it persist state, switch an active project, affect later calls?) or what 'create' changes on disk. For a tool flagged destructive, the agent needs more than a parameter-to-action mapping.

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?

Two compact sentences with no filler, and the per-action parameter mapping is front-loaded. The compression borders on cryptic ('List selected projects with offset/limit'), but every clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be described, and the parameter mapping is covered. What is missing is adequate treatment of the mutation side: with destructiveHint=true and three action modes, the definition should say what select/create change and whether path must already exist. Adequate but with clear gaps for a tool of this behavioral weight.

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 only 25% – only path is documented in the schema – so the description must compensate, and it largely does: it explains limit/offset as pagination for listing and path as the selector for select/create. The action enum values are also enumerated by name in context. It still leaves the interaction (e.g. is path ignored when action=list?) and offset semantics implicit, but the coverage gap is meaningfully filled.

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 names the resource (projects) and three distinct operations (list, select, create), and even maps parameters to operations ('offset/limit' for list, 'path' for select/create). It is specific about action scope, though the phrase 'List selected projects' is slightly ambiguous about what a 'selected' project is. It does not differentiate against siblings like codex_list or codex_sessions, which is why it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implicit guidance exists: 'select/create takes path' tells the agent which parameter belongs to which mode, and 'The main agent chooses an absolute project directory' signals a constraint on how path is supplied. However, there is no when-to-use versus alternatives, no exclusion of related tools, and no statement of preconditions for select versus create.

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