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

Beyond the destructiveHint and readOnlyHint annotations, the description adds critical behavioral details: the operation is irreversible, it cascades to linked deep dives, and it is restricted to owned research. This is exactly the kind of context an agent needs before invoking a destructive tool.

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 compact and front-loaded: the core action appears first, followed by necessary caveats. Every sentence adds value, covering cost, ownership, cascade behavior, and irreversibility without unnecessary detail.

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 simple one-parameter delete operation with no output schema, the description is complete. It covers what is deleted, who can delete it, what else gets deleted, and that the action cannot be undone.

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 schema already fully documents the single `id` parameter with type, format, pattern, and a description. The tool description adds little parameter-specific meaning beyond saying 'by ID,' so the baseline score of 3 applies.

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 action, 'Delete a specific research by ID,' with a clear resource and identifier. It distinguishes itself from sibling tools like delete_deep_dive and delete_brand_names by naming 'research' as the target resource.

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 gives clear usage context: it can only delete research owned by the authenticated user, and it mentions the cascade behavior for linked deep dives. It does not explicitly name alternatives or say when not to use it, but the ownership restriction effectively defines a boundary.

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