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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description adds what the annotations cannot: that the deletion is irreversible ('This cannot be undone') and that it cascades to all generated PDFs. That cascade scope is the key behavioral fact an agent needs before invoking.

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?

Three short sentences, front-loaded with the destructive scope and consequence before the usage guard. Every sentence carries a distinct, necessary piece of information.

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 single-parameter destructive tool with no output schema, the description covers the effect, the cascade, irreversibility, and the invocation precondition. Nothing an agent needs to call it safely is missing.

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 a single parameter at 100% schema coverage, the schema already documents application_id fully, including its UUID format and origin from create_application. The description refers to 'that draft' only implicitly and adds no format or sourcing detail beyond the schema, so the baseline 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?

States a specific verb (permanently delete), the resource (a user's draft/application), and the cascade scope ('every PDF generated from it'). This distinguishes it from siblings like update_application or get_pdf_download without needing the schema.

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?

Gives an explicit gating condition: 'Only call it when the user explicitly asks to delete that draft,' which functions as a when-not rule, and adds a required confirmation step ('confirm which one first'). No alternative delete tool exists among the siblings, so there is nothing further to disambiguate.

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