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

Annotations already flag destructiveHint and idempotentHint, but the description adds real behavioral detail: click history is destroyed, the short link stops resolving within a minute, the ending becomes reusable, and the user must be signed in. That is meaningful context the annotations cannot express.

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?

A single tightly-packed sentence front-loads the destructive action, then the timing and auth constraints, then the alternative. No filler and no repetition of the title.

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, no-output-schema mutation, the description covers everything an agent needs: irreversibility scope, timing of effect, auth requirement, confirmation guidance, and a non-destructive alternative. Nothing material 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 description coverage is 100% and the single `link` parameter already documents the accepted forms (full URL, ending, or id), so the description adds nothing further. Baseline 3 is appropriate when the schema fully carries parameter semantics.

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 and resource ("Permanently deletes one of the user's Snip links and its click history") and clarifies scope beyond the name by noting that click history goes too. It also implicitly distinguishes itself from update_link, which handles pausing.

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?

Explicitly tells the agent to confirm with the user first and names the alternative action ("to pause a link instead, use update_link with disabled true"). This covers both the when and the when-not with a concrete sibling route.

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