Export the recovery words

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

Discloses critical consequences beyond the annotations: the words persist in the conversation, anyone who sees them can take the funds, and the operation is local with no network. readOnlyHint/idempotentHint correctly reflect that nothing is mutated, so there is no contradiction and the risk disclosure adds real value.

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?

Three dense sentences, front-loaded with what is exported and what it controls, followed by the gating condition and the risk. 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 no-output-schema secret-export tool, the description covers the risk, the confirm gate, and network locality. It leaves the preview mode (confirm omitted/false) unmentioned, a minor gap for an agent deciding whether a bare call is safe.

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 the confirm boolean and its semantics are already documented in the schema. The description reinforces the confirm: true requirement but omits the schema's 'omitted or false = preview only' behavior, so it adds little beyond the baseline.

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 ('Show this agent's 12-word BIP39 mnemonic') and immediately scopes what it controls (identity and every order's escrow key). This is clearly distinguishable from siblings like wallet or registry_entry 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?

Gives a clear selection condition ('use only when your human asks for a backup') and a hard gate ('Only with confirm: true'). It does not name an alternative tool for non-backup identity inspection, so it is clear context rather than full when/when-not routing.

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