start_signin

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

Beyond annotations, it discloses that the tool opens the user's browser, polls for up to ~45s, never opens a second window on repeat calls, and maps outcomes to next actions. These are important operational traits for an auth-recovery tool and do not contradict 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 front-loaded with the core purpose, then gives the trigger condition, approval requirement, polling behavior, and outcome-specific next steps. Despite being detailed, every sentence adds actionable guidance and there is 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 complex auth-recovery workflow with no output schema and only sparse annotations, the description supplies the missing completeness: trigger, confirmation, timeout, repeat-call semantics, retry behavior, and the headless-environment failure path. An agent has enough information to invoke and follow up correctly.

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 schema has 100% description coverage and fully documents the single `intent` parameter, including privacy constraints. The description does not add further meaning about `intent`, so the schema carries parameter semantics and the baseline 3 applies.

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 verb and resource: fix a broken DoorDash sign-in by launching `dd-cli login` without sending the user to a terminal. It clearly distinguishes this from the many ordering/account sibling tools, none of which handle authentication recovery.

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?

It gives explicit when-to-use conditions: a tool fails with 'sign-in is missing or expired' AND the user wants to continue after approving a confirmation prompt. It also specifies follow-up behavior for each outcome and explicitly says NOT to call again on `browser_signin_unavailable`.

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