Click

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

No annotations are provided, so the description carries the full behavioral burden, and it does disclose substantial behavior: real mouse events, occlusion detection (skips and reports the covering element), navigation-triggered loading waits, new-tab reporting, file-picker interception, and non-handling of <select>. However, it says nothing about permission/auth requirements, failure/error reporting beyond occlusion, or whether the action is irreversible. The disclosure is strong but the no-annotation baseline leaves gaps that a 4-5 would require closing.

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 dense sentences, zero filler, front-loaded with the primary action and its occlusion caveat before the secondary routing notes. Each clause conveys a distinct behavioral fact an agent needs.

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 an 8-parameter, no-output-schema, annotation-free action tool, the description covers the highest-risk behaviors (occlusion, navigation waits, file pickers, select dropdowns). It stops short of describing error returns and multi-slot/agent coordination semantics, which are left to the schema, leaving a small but real completeness 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 description coverage is 100% across all 8 parameters (ref, tab, read, slot, agent, double, summary, multiSlot), so the schema already documents everything. The description adds only the implicit meaning of "ref element" (matching the schema's browser_snapshot ref), which does not exceed the structured field. Baseline 3 is correct 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?

States a precise verb+resource ("Clicks a ref element with real mouse events") and immediately bounds the scope against siblings: it does not click <select> dropdowns and routes those to browser_select. An agent can distinguish it from browser_type, browser_fill, browser_select, and browser_upload without opening any schema.

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?

Explicit when-not and alternative routing: file inputs/attach buttons are intercepted, so use browser_upload; <select> dropdowns are not handled, so use browser_select. This is exactly the when/when-not/alternatives pattern that lets an agent pick the right tool on the first try.

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