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

With no annotations the description carries the full burden, and it delivers: credential substitution, https-only posting inside allowed hosts, encrypted cookie storage, an opaque session id return, scope/daily-cap enforcement, audit logging, CAPTCHA/new-device handling, and free-tier dry-run behavior. This is rich behavioral disclosure an agent cannot get from the schema.

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?

Dense but front-loaded: the core action and its non-exposure guarantee come first, then mechanics, then limits and edge cases. Every clause carries information, though the single long sentence crams several concerns together and could be split for easier scanning.

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 6-parameter mutation-style tool with nested objects, no annotations, and no output schema, the description covers the return value (opaque session id), the safety profile (scope/cap checks, audit log), and the failure path (CAPTCHA → request_human). Nothing an agent needs to invoke it correctly is missing.

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 coverage is 100% so the baseline is 3, but the description adds meaning the schema lacks: url must be https and inside the login's allowed hosts, and the {{username}}/{{password}}/{{totp}} placeholders are resolved server-side from the saved login. That extra constraint context justifies going above baseline.

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 verb and resource ('Sign in with a saved login') and immediately distinguishes itself from save_login/list_logins/end_session by making clear it performs the actual authentication using stored credentials without exposing them. The scope ('without seeing it', placeholders filled server-side) is uniquely identifiable.

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?

Gives concrete conditions: it is checked against the login's scope and daily cap, and on CAPTCHA/new-device it suggests next_step request_human (Human Handoff relay). It also flags the free-tier behavior ('watch-only logs would_use_vault and signs in nowhere'). It stops short of explicitly naming sibling alternatives, but the context is clear enough to select it correctly.

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