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

Annotations already mark this destructive and non-read-only. The description adds real behavioral context beyond annotations: the two-phase preview/confirm model and that dependent tasks survive the deletion. It stops short of describing reversibility or permission requirements.

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 compact sentences, front-loaded with the action and its side effect, then the confirmation requirement. Every clause 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?

No output schema, so the description should carry return behavior — it does explain the preview vs. execution outcome. Given annotations covering destructiveness and a small 2-param schema, this is nearly complete; only auth/reversibility detail 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?

Schema coverage is 50%; the description compensates for the undocumented templateId (implied target) and reinforces confirm's exact semantics. The schema already spells out confirm's behavior, so the description largely echoes it, but it adds the preview-framing which is genuinely useful.

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+resource ('Deletes a card template') and immediately disambiguates from other delete tools by clarifying the effect on derived tasks ('tasks made from it stay'), which is the key distinguishing behavior versus delete_task or delete_board.

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?

Clearly explains the confirm semantics — without confirm:true you get a preview rather than the deletion. It does not, however, explicitly route to siblings (e.g., archive vs delete) or state when deletion is preferred over archiving.

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