Delete Excalidraw project

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

With zero annotations, the description carries the full behavioral burden. It does disclose a meaningful trait: the deletion is guarded by exact path confirmation and a base revision check, signaling a deliberately protected destructive operation. However, it stays silent on whether deletion is permanent or recoverable, how a stale revision mismatch is handled, and what happens to the project's canvases and assets on deletion.

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?

A single 10-word sentence front-loads the action ('Deletes a managed project') and packs the key safety qualifier into a compact dependent clause. Every word earns its place; there is no filler, no repetition of schema content, and no preamble.

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 destructive operation with four required parameters and zero annotations, the description is thin. An agent invoking this tool would still need to know whether the deletion is irreversible, what happens on revision mismatch, whether canvases under the project are cascade-deleted, and what the success/failure response looks like. The description answers only the 'what' and the minimal 'guarded by confirmation' part, leaving high-stakes operational questions open.

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 only 50%: projectPath and confirmProjectPath have descriptions, while baseProjectRevision has only a regex pattern and mutationId has no description at all. The description's 'exact path and revision confirmation' adds meaning by clarifying the two path parameters as a confirmation pairing and the revision as a concurrency guard. It does not explain why two identical path fields are required or what mutationId is for (e.g., idempotency).

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 states a specific verb ('Deletes') and resource ('managed project'), making the tool's core action unmistakable. The qualifier 'after exact path and revision confirmation' adds the distinguishing safety mechanism. It differentiates cleanly from siblings like rename_project, duplicate_project, and delete_canvas, though the term 'managed' is never defined, leaving minor ambiguity about which projects qualify.

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 implies the usage context: call this when a managed project must be deleted and confirmation data is available. However, it provides no explicit when-not-to-use guidance, no mention of alternatives like delete_canvas for smaller-scope deletions, and no statement about whether this should be chosen only as a final action. The guidance is present only by implication.

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