QuantConnect

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

Annotations provide idempotentHint=true, indicating safe retry behavior, but the description adds minimal value beyond this. It confirms the destructive nature ('Delete') which aligns with the tool name, but doesn't elaborate on permissions needed, whether deletion is permanent, what happens to associated resources, or error conditions. With annotations covering idempotency, the description meets a low bar but lacks rich behavioral context.

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 extremely concise - just three words - with zero wasted language. It's front-loaded with the essential action and resource. While it lacks detail, every word earns its place by communicating the core function without redundancy.

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 idempotentHint annotation and an output schema (though unspecified here), the description is inadequate. It doesn't explain what 'delete' entails (permanent removal? archiving?), doesn't mention authorization requirements, doesn't warn about consequences, and provides no usage context. The annotations help slightly, but the description leaves critical gaps for a mutation tool.

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?

With only 1 parameter and 0% schema description coverage, the description doesn't mention the projectId parameter at all. However, since there's just one required parameter (projectId) and the schema's $defs provides a clear description ('Id of the project to delete'), the agent can reasonably infer usage. The description's omission is less critical here than with multiple undocumented parameters.

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 'Delete a project' clearly states the action (delete) and resource (project), making the basic purpose understandable. However, it doesn't differentiate from sibling tools like delete_backtest, delete_file, delete_object, or delete_project_collaborator, leaving ambiguity about what specifically distinguishes this deletion operation from others in the system.

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 provides no guidance on when to use this tool versus alternatives. There's no mention of prerequisites (e.g., project must exist, user must have permissions), consequences (e.g., irreversible deletion), or relationships with sibling tools like delete_project_collaborator or create_project. The agent receives no usage context beyond the basic action.

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