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

With no annotations available, the description carries the full burden and does so: it declares login requirement, irreversibility, exactly what is destroyed versus retained, default preview mode, a two-phase confirm-then-execute protocol via previewHash + consent=true + preview=false, and rejection on ownership/version drift. That is unusually thorough behavioral disclosure for 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?

Very dense but front-loaded: login requirement, deletion scope, prerequisite tool, then the execution protocol. Almost every clause carries unique operational information, though the telegraphic style ('同参') compresses the confirm step enough to require a second read.

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 4-parameter tool with no annotations and no output schema, the description covers the precondition, the preview/confirm/execute lifecycle, and the failure mode (ownership/version changed). It stops short of describing what the preview returns (e.g. the hash) or how to surface it to the user before confirming.

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 only 25% (only companyId documented), so the description compensates well: it clarifies that previewHash comes from the preview call and must be passed with 'same params', that consent must be true, that preview=false triggers the real delete, and that preview defaults to true. Only the exact previewHash derivation/format is left implicit.

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 scope: hard-deletes only the caller's own company page plus its audit records, irreversibly, while preserving account/profile/products. This crisply separates it from soft-delete/archive behavior (e.g. archive_my_company) and from update_my_company without needing 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?

Gives real routing conditions: requires login, call get_my_company first, defaults to preview, and use this tool only when the user explicitly asks for full deletion. It does not explicitly name the alternative (archive_my_company) for non-hard-delete cases, so it falls just short of a full when/when-not/alternatives treatment.

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