login

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

The description discloses a wealth of behavior beyond the annotations: the tool returns before login completes, it opens a real visible window, it may reuse an existing browser session, it may sign out that profile if no usable credential exists, and it refuses when STOCKBIT_NO_BROWSER is set or when a session is already stored unless force is true. It also explains token storage (keychain/encrypted file) and that the token is never shown. This is rich, honest behavioral disclosure.

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 every sentence earns its place. It is front-loaded with the most important instruction (ask first, confirm:true), and each paragraph covers a distinct topic: behavior/timing, token storage, existing-session handling, switch_account, refusal conditions, and trading-login distinction. The structure is clear and scannable for an agent.

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 complexity — interactive login, side effects, timing, refusals, and a distinction from trading login — the description covers all the operational context an agent needs. There is no output schema, so explaining the immediate return value and the need to poll status is essential, and it does exactly that. No important call-time behavior is left undocumented.

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?

Although the schema already provides descriptions for all 4 parameters (100% coverage), the description adds critical semantic context: confirm must be true and only after asking; switch_account implies force and signs the current account out; fresh_profile is for corrupted profiles and not for switching accounts. The description clarifies the relationship between parameters and their real-world consequences, which goes well beyond the schema.

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 that this tool opens a browser window for the user to sign in to Stockbit, and distinguishes it from trading-account login (which requires a PIN). It also differentiates from related tools like status (checking login state) and logout (signing out), so an agent can tell what this tool does and what it doesn't.

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 gives explicit when-to-use instructions: ask the user first, call with confirm:true, and use switch_account:true for a different account. It also names alternatives and exclusions: use status to verify, do not call again while status says login is in progress, and this does not log in to the trading account — that requires stockbit-auth trading-login. This is exemplary usage guidance.

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