cw_project

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

With zero annotations the description carries the full burden, and it does disclose the most important hazard: close and revert discard the session with no undo and are gated behind a confirm key. It stops short of covering the other commands' side effects — whether open replaces the current session, whether save overwrites the file on disk, whether exportAudio writes output — which a mutation tool with no annotations should ideally state.

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?

Two tight sentences, with the command list and the destructive-confirm warning front-loaded; nothing is buried. The verbatim re-listing of the enum is mild duplication of the schema, but it is cheap and aids scanning.

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 two-parameter tool with no output schema and no annotations, the definition covers the safety story but leaves a conspicuous hole: open, saveAs, importMidi, and exportAudio presumably need a file target, yet the schema exposes only command and confirm and the description never explains how a file is selected (dialog?) or what state the tool returns. Adequate, but an agent could not confidently invoke the file-oriented commands from this text alone.

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 coverage is 50% and the confirm parameter's schema description already says it must equal the command name, so the description largely restates structured data. It does add the 'why' — that the confirm gate exists because these commands discard the session irreversibly — which is real value, but the command parameter itself gains no interpretation beyond the schema enum.

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?

States a specific verb and resource ('Run a document command') and enumerates the eight supported commands, so the agent knows the exact operation set. It does not distinguish this from lookalike siblings such as cw_run_command, cw_save_state, or cw_document_state, leaving the agent to guess which entry point is canonical.

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 description gives one explicit usage rule — close and revert refuse unless confirm is set to the command's own key — which is genuinely actionable. But it offers no guidance on when to reach for cw_project versus cw_run_command or the state-inspection siblings, and no prerequisites for commands like open or saveAs.

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