Check whether a project is safe to write

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

With no annotations provided, the description must fully disclose the tool's behavior. It does list the exact checks performed and the verdict types, which is good. However, it does not explicitly state that the tool is read-only/does not modify the project, nor does it explain what happens after a 'refuse' verdict (e.g., whether the write is blocked). This leaves some ambiguity, so the description earns a moderate score rather than higher.

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?

The description is two sentences. The first sentence is dense but information-packed, listing all major checks and the verdict scale. The second sentence is a direct imperative on usage. Every word earns its place; there is no padding or repetition.

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?

Given the tool has one parameter and no output schema, the description provides substantial context: it lists the checks performed, the verdict values, and the explicit instruction to run before writing. It does not describe the return format or error behavior, but for a pre-write guard with this level of detail, it is almost complete. The lack of output schema is partially mitigated by the verdict enumeration.

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 100%: the parameter 'project' has a description 'Path to the project folder or its draft_content.json'. The tool description adds context that this project is checked for compatibility, but it provides no additional syntax, formatting, or constraint details beyond the schema. Baseline 3 is appropriate because the schema already fully documents 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 clearly states the tool's purpose: to produce a verdict (ok/warn/refuse) on whether a project is safe to modify. It enumerates specific checks (CapCut vs JianYing, upstream write guard, editor running, storage-mirror agreement, lint errors, ffmpeg/ffprobe). This distinguishes it from sibling tools that perform modifications (add_overlay, render_overlay) or inspection (inspect_project).

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 explicitly says 'Run this before writing,' which is a clear directive for when to use the tool. It doesn't explicitly list alternatives or when not to use it, but the context of sibling write tools implies it's a pre-flight check for those operations. This is sufficient guidance for an AI agent to sequence the tool appropriately.

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