auth_read

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

Goes well beyond the readOnlyHint annotation: DNS is re-resolved on every call, unconfirmed origins are refused, long text is truncated, and cookies/storage are never returned. These are exactly the operational facts an agent needs before invoking it.

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?

Five terse sentences, each carrying a distinct constraint (mode, DNS, origin refusal, truncation, non-return of secrets). The primary purpose is front-loaded and nothing is padding.

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?

With no output schema, the description partially covers return behavior (visible text only, truncated, no cookies/storage). The main remaining gap is what the response looks like structurally and how truncation is signaled, but the essential call-correctness information is present.

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 all three parameters are already documented, including that url must be on a confirmed origin. The description restates the confirmed-origin constraint for url but adds nothing about selector, so it is on par with the schema rather than additive.

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 ('Read visible text from this site's current page') plus the conditional navigation mode when url is set. This is clearly distinguishable from auth_open, auth_act, and auth_status among the siblings.

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?

Explains the two modes of use (read current page vs. navigate-then-read when url is set) and the gating condition (origin must be human-confirmed). It does not explicitly contrast with auth_open/auth_act for navigation or reading after actions, so an agent must infer which sibling to prefer.

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