app_discover

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

With no annotations at all, the description bears full responsibility for behavior. 'Ask the running page' and 'actual interactive surface' make clear this is an inspection/discovery operation that reports on the live page rather than mutating it, and the inclusion of 'working selectors' discloses a key deliverble. It does not explicitly state side-effect-freedom or prerequisities, but the read-only intent is strongly conveyed.

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?

Two sentences, no filler. The first sentence front-loads purpose and concrete output categories; the second supplies a usage rule and rationale. Every clause earns its place.

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 no-parameter tool with no output schema, the description covers what the agent needs: when to call, why, and what will be returned. It could add the exact response shape or mention that a devtools/page connection is required, but those dependencies are reasonably inferred from sibling tools like devtools_connect and page_navigate.

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 tool has zero parameters and an empty schema, so there is no parameter documentation burden. The description's only input-related obligation is to make clear the tool takes no arguments and can be invoked immediately, which it implicitly does.

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 ('Ask the running page what it is') and enumerates the exact information categories reterned: UI libraries, routing, frame count, and interactive elements with selectors. This clearly distinguishes app_discover from sibling DOM/UI tools like ui_click or dom_quer, which operate on known selectors rather than discovering an unfamiliar page.

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 timing and context—'Call this once before driving an unfamiliar app'—and warns against guessing selectors. It does not name an alternative tool or give a when-not-to-use condition, but the intended placement in the workflow is unmistakeable.

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