Press key on page element

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

Annotations already indicate destructiveHint=true and readOnlyHint=false, but the description adds valuable behavioral details: error handling (returns OPERATION_TIMEOUT) and that it does not close MCP or browser sessions on failure. This goes beyond the annotations and provides actionable information for an agent. 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?

Two sentences, both directly relevant. The first states the action and a key behavioral constraint (deterministic ordering). The second covers error handling and session preservation. No clutter or redundant phrasing.

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 description covers the main action and error behavior, and an output schema exists (so return format is handled elsewhere). However, with six parameters and zero schema descriptions, the description does not fully compensate for parameter ambiguity. It is adequate but not thorough for a mutation tool with destructive annotations.

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 0%, so the description must compensate. The description only mentions timeoutMs ('within timeoutMs (10 seconds by default)') and implies 'locator' but does not explain sessionId, pageId, key, ref, or the locator structure. This is a significant gap; the agent cannot infer parameters from the description alone.

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 clearly states the action: 'Press a key on a locator within one explicitly addressed page'. It also distinguishes this from siblings like browser_click (mouse action) and browser_fill (text input) by focusing on keyboard key presses. The verb and resource are specific, and the phrase 'within one explicitly addressed page' adds scope.

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?

The description gives context about usage: it operates on a specific page and preserves deterministic ordering with other operations. However, it does not explicitly mention alternatives or when not to use this tool (e.g., when to use browser_fill or browser_click instead). The context is clear but lacks explicit exclusions or comparison to siblings.

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