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

Annotations already cover the safety profile (destructiveHint=true, idempotentHint=false), but the description goes well beyond them: it enumerates exactly what is destroyed, states irreversibility, documents the two-step confirm handshake including that the first call is a no-op that returns a warning, and gives non-retry guidance on error/timeout with a verification alternative. This is exactly the kind of context annotations cannot convey.

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?

Front-loads the destructive scope and irreversibility, then the usage gate, then the two-step protocol and failure handling, closing with the endpoint. Six sentences, none of them filler — every clause carries either a constraint or a recovery instruction.

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?

There is no output schema, but the description fills that gap by stating what the first call returns (the warning to show the user) and what a failure implies. For an idempotency-unsafe destructive tool with 2 params, nothing an agent needs to call it safely 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 coverage is 100%, so baseline is 3, but the description adds real semantics the schema does not: confirm must be the account email typed by the user themselves after reading the warning, and omitted entirely on the first call. The safety meaning of the email/confirm pairing is clarified beyond the field descriptions.

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 everything on a Muse account") and enumerates the exact scope — chats, files, documents, web apps, podcast, memory, name. This distinguishes it cleanly from the many sibling deletion tools (muse_delete_chat, muse_delete_file, muse_delete_asset), which are narrower.

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?

Explicit when-to-use ("only when the user explicitly asks to reset the account"), an explicit when-not (never fill confirm on your own), and an explicit alternative path after failure (check with muse_get_account or muse_list_chats). It even names the pre-condition that must hold before the second call.

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