project_health

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

With no annotations, the description carries the burden of explaining behavior. It adds useful context by listing the audit domains and specific issue types detected, and 'audit' suggests a non-mutating diagnostic. However, it does not explicitly state that the tool is read-only, what the output format is, or whether it can take significant time.

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 a single, front-loaded sentence that packs in the action, scope, and purpose without wasted words. The '[HIGH_LEVEL]' prefix is minor metadata, but the rest of the sentence is dense and useful.

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 tool with no parameters, invocation is trivial, but the description does not fully explain what the audit returns, whether it modifies anything, or how it relates to the many similar project/scene audit tools. Since there is no output schema and no annotations, these missing details keep it from being complete.

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?

The tool has zero parameters, so the baseline is 4. There is no parameter information needed, and the description does not need to compensate for any schema gaps.

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 ('Runs an automated audit') and names both the resource (project health) and the audit scope (scripts, instances, physics, remotes). It clearly conveys what the tool does, but it does not explicitly differentiate it from close siblings like project_analyze or project_repair.

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?

There is no guidance on when to use this tool versus alternatives such as project_analyze, project_repair, or diagnostics_safe_repair. The description only implies that it should be used when a health audit is desired, but it gives no exclusions or routing heuristics.

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