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

Annotations declare destructiveHint/idempotentHint but say nothing about blast radius or safety protocol. The description adds the cascade effect across all contacts, states that the first call deletes nothing, and mandates user consent before the destructive call — exactly the context annotations cannot convey.

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, no filler, and the highest-stakes information (deletes from every contact) is front-loaded before the procedure. 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?

For a destructive, open-world tool with no output schema, the description covers consequence and required user flow, which is the essential burden. Minor gap: dry_run and its precedence over confirm are only in the schema, and nothing is said about the preview payload or failure behavior.

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 tag_id, confirm, and dry_run are already fully documented, including the 'leave false first for a preview' wording. The description reinforces the confirm handshake but never mentions dry_run or how it interacts with confirm, so it adds little beyond the schema. 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+resource ('Delete a contact tag') and immediately adds the scope that matters: it is removed from every contact that has it. That scope line distinguishes it from remove_tag_from_contact (single contact) and update_tag without the agent needing to open sibling schemas.

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 procedural protocol: call first without confirm for a preview, obtain an explicit user yes, then call again with confirm: true. The cascade scope in sentence one implicitly routes single-contact removals elsewhere, but no sibling is named outright, so it falls just short of full alternative guidance.

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