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

Annotations already declare destructiveHint=true and idempotentHint=true, yet the description still adds substantial behavior: the dependency-based refusal rules, the mandatory confirm sequence, and the required role. That is exactly the kind of 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?

Three dense sentences with no filler, and the destructive warning is front-loaded. The phrasing 'put the sentence it answers to the person' is slightly awkward and costs a little clarity, but nothing is wasted.

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, the description covers purpose, refusal conditions, the confirm protocol, and authorization. An agent has everything needed to call it safely and correctly.

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 both tagId and confirm are already fully documented in the schema, including the meaning of confirm. The description's confirm language largely mirrors the schema rather than adding new parameter-level meaning, 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+resource ('Deletes a tag') and immediately bounds the scope ('nothing depends on' it), plus the refusal condition. It names the sibling surface it mirrors ('as Delete on Manage tags does') and implicitly separates itself from merge_tags/rename_tag/delete_project. An agent can distinguish it without opening another 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 when-to-use and when-not: only tags with no dependents; tags carried by a project or matched by a rule are refused. It also prescribes the exact two-call confirm workflow and names the authorization gate (Owner and Admin), leaving nothing to inference.

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