auth_open

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

With no annotations, the description carries the full burden and does so well: it discloses DNS re-resolution with address pinning, fail-closed behavior when the connected address falls outside the checked set, the human_action_required return path with suppressed page text on login/challenge pages or unconfirmed final origins, and blocking of subresource requests to link-local/metadata hosts. These are exactly the non-obvious safety traits an agent needs.

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?

Four compact sentences, each carrying distinct information, with the core action and the origin precondition front-loaded. Density is high and there is little waste, though the middle sentences pack multiple clauses that slightly reduce scannability.

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 security-sensitive tool with no annotations and no output schema, the description covers preconditions, failure modes, and the human_action_required return path well. It leaves the success return value implied rather than stated and does not explain how the opened page relates to subsequent auth_read/auth_act calls, a minor gap.

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 both parameters (site, url) are already fully documented with formats and constraints. The description's phrase 'confirmed origin' loosely constrains the url parameter but adds no syntax or format detail beyond the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

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 a concrete verb and resource: 'Open a URL in that site's Chrome profile.' That is unambiguous about the action and the per-site Chrome profile scope. It does not explicitly contrast itself with siblings like auth_read or auth_act, so an agent must infer when opening differs from reading or acting.

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?

It states a hard precondition: the origin must already be human-confirmed (login origin or work origin), which tells the agent this tool must follow auth_confirm/auth_login rather than being a first step. It gives clear context but names no alternative sibling or exclusion, so routing between auth_open and auth_read/auth_act is not spelled out.

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