login

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

Discloses important behaviors beyond the annotations: it creates a personal API key named 'claude-code', stores it, uses the password only once, and replaces any current connection. Since annotations only provide basic flags, the description fully carries the behavioral transparency burden.

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 concise, information-dense sentences with no filler. The purpose is front-loaded, followed by side effects and alternative routing.

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?

Covers the auth flow, key creation, password handling, and connection replacement, which is sufficient for a two-parameter tool. It does not describe output or error behavior, but no output schema exists and that is a minor gap rather than a blocking omission.

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 already documents password as used once and never stored; the description mostly restates email and password without adding deeper semantics for the email parameter. With 50% schema coverage, the description provides only modest additional value.

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?

States a specific action: connecting the machine to an existing TaskLite account using email/password, and switching accounts. It also differentiates itself from the sibling 'connect' by noting the alternative applies when the user already has a tl_ key.

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?

Clearly says to prefer 'connect' when the user already has a tl_ key, which is explicit routing to an alternative. It also implies login is for existing accounts rather than sign-up, but it does not explicitly mention sign_up or disconnect exclusions.

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