start_login

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

With no annotations, the description carries the full burden and does so thoroughly. It discloses channel-dependent return shapes, empty deep_link on SMS, possible missing or empty sms_dids entries, email_sent failure semantics, and the fragility of qr_text when wrapped. It also lists terminal session states, giving complete behavioral transparency.

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 long but tightly structured with numbered agent steps and explicit channel-based branches. The core purpose and return fields are front-loaded, and every subsequent detail — including sms_dids edge cases and qr_text wrapping rules — is actionable rather than padding.

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 tool with no output schema and no annotations, this description is unusually complete. It covers per-channel return values, follow-up polling with wait_for_login, terminal states, failure detection, and rendering constraints. An agent has enough information to invoke the tool correctly and handle all documented outcomes.

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 baseline is 3. The description adds essential cross-parameter meaning by clarifying that phone_number is required for SMS and email for email, and that the selected channel determines which returned fields are relevant. This goes beyond the schema's generic 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?

The description states a specific action — starting a login session by sending an authentication challenge — and enumerates the supported channels. It also distinguishes itself from related siblings by explicitly telling the agent to call wait_for_login afterward and referencing render_auth_link for presenting links.

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 numbered agent usage gives an explicit workflow: call start_login, then wait_for_login. It provides channel-specific instructions, including when to pass deep_link to render_auth_link versus showing sms_message, and warns that render_auth_link rejects the empty SMS deep_link. It also instructs checking email_sent before assuming email delivery, which is clear when/how usage guidance.

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