load_project

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

Annotations are all false, so they don't guarantee file safety; the description adds the valuable disclosure 'The input file is never modified,' resolving ambiguity around readOnlyHint=false. It also surfaces the CX_MCP_ALLOWED_ROOTS environment variable, giving the agent actionable knowledge about filesystem access restrictions.

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?

Three short sentences, each earning its place: the purpose, the file-safety guarantee, and the security configuration note. No redundancy with the schema or annotations, and the core purpose is front-loaded.

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?

For a low-complexity tool (1 parameter, output schema present), the description covers purpose, file types, safety, and security. It stops short of explaining session lifecycle behavior (e.g., what happens when loading a new project while one is already open), which is a minor gap given the editing-session framing.

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 description coverage is 0%, so the description must compensate. It does so by specifying that the tool loads '.CXP or .CXT' files, which tells the agent that the required 'path' parameter must point to one of these file types. This is the key semantic constraint on the parameter.

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 uses a specific verb+resource construction: 'Load a CX-Programmer .CXP or .CXT into an offline, in-memory editing session.' It clearly names the input format and the destination context, and it differentiates itself from siblings like save_cxt, close_project, and launch_in_cx_programmer.

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 phrase 'offline, in-memory editing session' provides clear context that this is the foundational step for subsequent in-memory edit tools, and distinguishes it from launch_in_cx_programmer. However, no explicit alternatives or when-not-to-use scenarios are named.

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