Wait for something on the page

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

Annotations already carry readOnlyHint=true and openWorldHint=true, so the safety and non-determinism profile is covered. The description adds the useful AND-matching rule and condition types, but does not disclose what happens when timeout_ms expires (error vs. graceful return) or that the call blocks until a condition matches or times out. No contradiction with annotations.

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?

A single 13-word sentence that leads with the verb and condition types, then appends the AND constraint. No filler, repetition, or buried detail; every word 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?

The core semantics, condition types, and combination rule are covered, and the 100% schema coverage plus readOnly/openWorld annotations carry the safety and parameter details. The clear gap is timeout-failure behavior and return shape, which matters for a blocking tool with no output schema — the agent cannot know whether a timed-out wait raises an error or returns a partial result.

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; the description adds the cross-parameter semantics the JSON schema cannot express — when multiple conditions are supplied, all must match. This clarifies the relationship between url, text, and selector beyond their individual field descriptions.

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 states a specific verb (wait for) and resource (page conditions), and enumerates exactly what it waits on: text, CSS selector, or URL, plus the AND rule for combining them. Among the 15 siblings, none is a blocking wait operation, so the purpose reads as distinct even though no alternative is named explicitly.

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?

No when-to-use or when-not-to-use guidance is given. The agent is not told to prefer waiting over polling with steel_snapshot or steel_find, and no prerequisites are stated beyond the schema's session_id description. The AND-matching note is the only usage hint, and it concerns parameter combination rather than tool selection.

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