Delete Card

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds materially more: the exact blast radius (comments, steps, and attachments are destroyed) and irreversibility ('cannot be undone'). For a destructive operation this is precisely the behavioral context an agent needs before invoking. No contradiction with annotations.

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?

Two sentences (~25 words) with zero waste: the action and blast radius are front-loaded, followed by a one-sentence irreversibility warning. Every word earns its place.

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?

The description is complete for selecting and invoking a simple destructive tool: it states the operation, consequences, and irreversibility, with both parameters documented in the schema. Minor gaps: no output schema so return/confirmation behavior is unstated, and the card_id ambiguity in the schema goes uncorrected.

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?

Schema coverage is 100%, so the baseline is 3, but the card_id schema description is self-contradictory: the property is named card_id yet the text says 'This is different from card_id' and conflates the visible card number ('#123') with the internal ID, which can mislead an agent on what value to pass. The tool description adds no clarification; only account_slug is well-documented.

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'), resource (card), and scope ('all its contents including comments, steps, and attachments'), which clearly conveys the operation and implicitly separates it from partial-delete siblings like fizzy_delete_comment and fizzy_delete_step. It does not explicitly name a sibling to distinguish from, so it falls just short of a 5.

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 destructive warning ('cannot be undone') implies this is for permanent removal rather than temporary state changes like fizzy_close_card, and the scope implies whole-card removal vs. deleting individual comments or steps. However, no explicit when-to-use, when-not-to-use, or alternative tools are named, leaving routing to inference.

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