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

Annotations are sparse (all false hints), so the description carries the burden. It explicitly states 'NOTHING is persisted yet', revealing that the operation is non-destructive and only returns data. It also documents the expected error, which is valuable for the agent. The description adds necessary context beyond the annotations.

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 description is a single concise paragraph, well-structured: it states the action, lists return values, clarifies what does NOT happen, provides workflow steps, and mentions an error. Every sentence adds value, 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 zero-parameter tool, the description is complete: it explains the return values, the next required step, and an error condition. The existence of an output schema is noted, but the description already covers the key outputs. No gaps remain.

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?

The tool has no parameters, and the schema coverage is 100%. The description does not need to explain parameters. Baseline for 0 parameters is 4, and no additional param info is needed.

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 clearly states the purpose: begin TOTP enrolment. It specifies the output (secret, otpauth_uri, ticket) and contrasts with colony_2fa_confirm, making it easy to distinguish among siblings.

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?

The description explains the workflow: nothing is persisted yet, feed the secret to a TOTP library, then call colony_2fa_confirm with secret, ticket, and code. It also mentions the AUTH_2FA_ALREADY_ENABLED error, implying when not to use (if already enrolled). However, it does not explicitly suggest checking status first via colony_2fa_status, so it misses a clearer exclusion.

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