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

Annotations only declare destructiveHint=true; the description goes further by stating the deletion is permanent, requiring user confirmation, and disclosing two blocking preconditions for sequences. This is exactly the extra behavioral context annotations cannot carry.

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 tight sentences: the destructive action and scope come first, then the safety and precondition caveats. Nothing is padded or redundant.

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 two-parameter destructive tool with no output schema, everything needed to invoke it safely is present: what gets deleted, where ids come from, confirmation requirement, and the blocking conditions.

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% and both parameters are fully documented (id plus a 4-value enum for type). The description restates the source of ids, which the schema already says, adding no syntax or format detail beyond it. Baseline 3 is correct.

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') and enumerates exactly which resources are covered (lead tag, pipeline stage, custom field, follow-up sequence), which separates it from sibling mutators like remove_tag or manage_stages. An agent can identify the operation without opening 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 explicit operating guidance: confirm with the user first, and take ids from get_account_setup. It also names failure conditions (sequence still used by a team, or the account's last sequence). It stops short of explicitly contrasting itself with sibling remove_tag/delete_* tools, so it misses a 5.

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