Browser Find

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

With no annotations, the description carries the full burden and does well: it discloses that matches are tagged with a ref using the '[data-mcp-ref="f1"]' attribute, that this is the same mechanism as browser_snapshot, and that the 'f' prefix prevents ref collisions between the two tools. That collision-avoidance detail is genuinely non-obvious. It doesn't state whether the operation is read-only or what happens in headless vs connect modes, leaving minor gaps.

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, front-loaded with the purpose and immediately followed by usage examples and the ref mechanism. Every clause earns its place, though the ref/collision explanation is dense and could be slightly tighter.

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 7-parameter, no-annotation, no-output-schema tool, the description covers the essential behavior an agent needs: how to call it and what the return refs mean and where to use them. It omits discussion of multiple/maxResults result-cap behavior, but that is fully documented in the schema.

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 adds concrete invocation examples – find({text: "sign in"}) and find({role: "button", text: "submit"}) – that demonstrate how text and role combine, which the schema alone doesn't show. It does not clarify mode/sessionId interaction (that sessionId skips mode selection is only in the schema).

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 (search/find) and resource (elements by visible text and/or ARIA role), and explicitly contrasts itself with browser_snapshot by noting no CSS selector or full DOM dump is needed. An agent can distinguish it from sibling tools like browser_get_element and browser_snapshot 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?

Gives clear context for when to use it (locating elements by text/role when you lack a selector) and names the downstream tools that consume the emitted refs (browser_click/type/hover/select_option), plus the sibling it replaces (browser_snapshot). It stops short of stating explicit exclusions or prerequisites, so it's clear but not fully routing.

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