acc_login

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

Goes well beyond annotations: describes non-blocking browser launch, always returning the authorization URL, callback port listening, token exchange and storage, the 45-second cap, the 'still waiting' response, and the 15-day session expiry. This rich behavioral context is critical for an agent to understand the async nature of the tool.

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 paragraph but covers many essential behaviors. It is front-loaded with the core purpose and then logically walks through the flow, wait behavior, and expiry. Some minor repetition (e.g., '~45 s' and 'capped per call') could be tightened, but every sentence adds useful information.

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 an OAuth tool with async browser interaction, the description fully covers what an agent needs: how to initiate, how to handle the wait/retry, and when to re-run. An output schema exists, so return-value details are not required. The description is complete despite the tool's complexity.

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 already documents all three parameters at 100% coverage. The description adds operational meaning: wait_only=true for polling, wait_seconds capped per call, and force_login behavior (prompt=login). This contextualizes the parameters without restating the schema text.

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 opens with 'Sign in with an Autodesk account (3-legged OAuth with PKCE)', a specific verb+resource pairing that clearly states the tool's function. It distinguishes from sibling auth tools like acc_logout and acc_auth_status by focusing on the login flow.

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?

Provides clear context on when to use the tool: to start an OAuth flow or re-authenticate after a 15-day expiry. It also gives explicit polling instructions ('call acc_login again with wait_only=true') when the wait times out. No explicit alternatives are named, but the guidance is sufficient for an agent to act.

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