Click an element by visible text

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

Annotations already cover the safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=true), so the description only needs to add nuance. It does: case-insensitive substring matching, multi-match disambiguation via index, and the important warning that some clicks have real-world effects ('Publish' really publishes) requiring user confirmation. It omits what happens on zero matches and whether it waits/retries for the element.

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?

Three short sentences, front-loaded with the core capability, then disambiguation, then the risk caveat in the position of greatest emphasis. The example list is short and illustrative rather than filler; no sentence is redundant with the name or schema.

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 two-parameter UI action with no output schema and full schema coverage, this is nearly sufficient, and the confirmation warning covers the main behavioral risk. The remaining gap is failure handling (no match found, multiple matches ignoring index, element not yet rendered) and the implicit precondition that a page is already open in the browser.

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, but the description genuinely adds meaning: the 'text' parameter is matched as a case-insensitive substring against both visible text and aria-label, which the schema's 'Visible text or aria-label' wording does not specify. It also clarifies index semantics with '0 = first', reinforcing the default.

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 (click) plus the resource classes it targets (button, tab, menu item, link) and the exact matching rule (visible text or aria-label, case-insensitive substring). That matching mechanism is what separates it from gsites_type and gsites_press_key, so an agent can pick correctly without opening a 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?

Gives concrete examples ('Publish', 'Pages', 'Insert') that tell the agent what kind of string to pass, and explains when to use 'index' rather than guessing. It also flags a confirmation requirement before consequential clicks. It stops short of explicitly naming alternatives such as gsites_press_key or gsites_type, or stating that a page must be open first.

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