discover_ui

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

With no annotations, the description carries the load and does add real context: it discloses that it clicks every enabled control, how screens are identified, and that it persists an inventory consumed by later tools. However it omits material behavior for a stateful crawler — that clicking live controls can mutate application state, that a target session must already exist, and that runs are bounded by state/depth caps.

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 dense sentences with the purpose front-loaded and the sequencing instruction at the end; every clause carries information. The middle sentence runs long with several comma-separated behaviors, which slightly hurts 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?

The output schema removes the need to describe return values, and the crawl concept is conveyed. But for a five-parameter, potentially state-mutating crawl with zero annotation coverage, leaving four parameters and the session/prerequisite situation unexplained leaves the definition only partially complete.

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 description coverage is 0% across five parameters, so the schema offers no help, and the description only explains `start` (named actions such as a sign-in). The meaning and effect of `fill`, `feature`, `max_depth` and `max_states` — especially the crawl bounds — are left entirely to inference.

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 — crawl the UI from the start screen, clicking every enabled control — and defines what it produces (a click[role:name] action per control plus an inventory). This clearly separates it from discover_cli and probe_web_field, and it names the downstream consumers (coverage, suggest_probes).

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?

"Start here, then probe fields and state rules" gives explicit ordering relative to the probe tools and establishes the entry-point role. It stops short of naming exclusions (e.g. when to choose discover_cli or open_target first), so not a full when/when-not treatment.

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