press_key

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

With no annotations, description only reveals it returns JSON with url and ref count. Does not disclose potential side effects like navigation or waiting behavior.

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?

Concise with clear Args and Returns sections. Every sentence adds value, no redundancy.

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?

Covers purpose, arguments, return for a simple key press tool. Could mention if key is case-sensitive or list valid keys, but adequate for basic usage.

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?

Given 0% schema coverage, description adds meaning: explains tab_id as handle from open_tab and key with example 'Enter'. Could list more key names or format.

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?

Clearly states it presses a single key in an open tab with examples like 'Enter', 'Tab', 'Escape'. Distinct from sibling tools like 'click' and 'type_into'.

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?

Provides explicit use cases: submit form, move between fields, dismiss dialog. Lacks explicit 'when not to use' or alternatives, but context from siblings implies type_into for multiple characters.

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