auth_poll

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

Without annotations, the description carries the behavioral burden. It explains polling behavior, pending state, and expiration. Could be improved by explicitly stating this is a polling endpoint with no side effects, but it is already transparent about the flow.

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 sentences cover the tool's purpose, input, possible outputs, and follow-up actions with no redundant information. Every sentence adds value.

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?

Given the tool's simplicity (one parameter, polling), the description fully covers the input, outputs, and the overall flow. It references the sibling `auth_start` tool for context, making it self-contained.

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?

Though schema coverage is 0%, the description adds full meaning: 'Pass the `device_code` from that response', specifying both the value's source and required format (minimum length implied). This goes beyond the schema's basic definition.

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?

Clearly states 'Complete the sign-in flow started by `auth_start`', specifying the verb (complete) and resource (sign-in flow). It distinguishes itself from the sibling tool `auth_start` by indicating it is the next step.

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?

Explicitly instructs to 'Pass the `device_code` from that response' and describes three return states (`signed_in`, `pending`, `expired`) with actions for each (call again or restart). Provides clear when-to-use and next steps.

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