project_eval

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

No annotations are provided, so the description carries the full burden. It discloses that code runs with full access to application modules, dependencies, and runtime state, which implies potential side effects. However, it stops short of explicitly warning about destructive operations or error handling, so a slight gap remains.

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 well-structured and front-loaded with the primary purpose, followed by a clear list of alternatives. Every sentence adds distinct value, and the bullet-point style improves scannability without verbosity.

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 that this is a general-purpose evaluation tool with no output schema, the description covers all essential context: what it does, when to use it, when to avoid it, what alternatives exist, and the level of access granted. It is sufficiently complete for an agent to decide and invoke correctly.

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 input schema provides 100% coverage for both parameters (code and timeout) with clear descriptions. The tool description adds context that the code executes within the running application, but doesn't elaborate on parameter syntax, defaults, or edge cases beyond what the schema already states.

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 evaluates Elixir code in the running application context, using the specific verb 'Evaluate' and naming the resource. It differentiates itself as a general-purpose escape hatch, contrasting with specific sibling tools like get_logs and recompile.

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 tells when to use project_eval (one-off operations with no dedicated tool) and when not to, providing a list of preferred alternatives for common tasks like logs, process info, recompilation, ETS data, docs, and callers.

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