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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds real value beyond them: reversibility depends on whether the provider has a trash bin, error 502 means the provider refused, and the operation requires a Pro plan. That is exactly the operational context an agent needs before invoking a destructive tool.

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?

The destructive warning is front-loaded, followed by parameter notes, reversibility, the safer alternative, and error semantics in tight order. Every clause carries distinct information with no filler.

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 impact, reversibility, tier requirement, error behavior, and an alternative. The only meaningful gap is the unexplained `connection_id` parameter, which an agent must guess or infer from siblings.

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 0%, so the description must carry the burden. It explains `key` as a path or provider id from list_files and `is_dir` as recursive folder deletion, but says nothing about `connection_id`, leaving one of three parameters undocumented. Partial compensation for the coverage gap warrants a 3.

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 ('Удалить файл или папку в облаке') and immediately flags the destructive nature in caps. It also distinguishes the folder case via `is_dir`, so an agent can separate this from siblings like move_file or execute_dedup 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?

Explicitly routes the duplicate-file case to execute_dedup because it guarantees a copy is kept, which is a genuine when-to-use-this-instead signal. It also points at list_files as the source of `key`. It lacks explicit when-not-to-use guidance for non-duplicate bulk deletions or shared resources, so it stops short of a 5.

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