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

Annotations already flag destructiveHint=true and non-idempotence, but the description goes well beyond them: it explains that trash is reversible while purge is not, that purge additionally destroys respondent-uploaded files, that a separate confirm_purge flag gates it, and that hidden/moderated answers are excluded. This is exactly the destructive-scope context an agent needs.

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?

Four front-loaded sentences cover action modes, reversibility, and exclusions with no filler. Minor redundancy ("irreversible is irreversible") keeps it just short of a 5, but sizing is appropriate for a multi-mode destructive tool.

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 six-parameter mutation tool with no output schema, the description covers what is destroyed, reversibility, the confirmation gate, side effects on files, and excluded categories. An agent has everything needed to invoke it safely; only auth/permission context is absent, which is a minor gap.

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 each parameter is already documented in the schema. The description reinforces confirm_purge's purpose and rationale (file deletion) but adds almost no syntax or format detail beyond what the schema states, so the baseline of 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?

The description names the resource (ответы/quiz answers) and the exact verb set it performs: trash, restore, or permanent delete. It explicitly distinguishes the three modes and states the exclusion (hidden and moderation-pending answers are untouched), so an agent can tell it apart from siblings like delete_answer_tag or toggle_answer_visibility.

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?

It clearly maps each action to its situation: normal deletion is reversible and lands in the trash, irreversible deletion requires confirm_purge and also removes respondent files. It does not name alternative sibling tools for adjacent tasks, but the when-to-use-each-action guidance is explicit.

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