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

Adds substantial context beyond the annotations: returns the URL and title after the press, Enter on account pages is refused, and sessions cost credits per started minute and end 3 minutes after the last call. These are real operational facts an agent needs that the destructive/openWorld annotations don't convey.

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?

Front-loads the core action and effect examples, then tacks on return value and cost/session notes. Every sentence carries real information, though the cost/session sentence is slightly dense and could be trimmed.

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?

Though there's no output schema, the description explains the return value (URL and title), the refusal rule, and session economics. For a single-param key-press tool, nothing an agent needs to invoke it correctly is missing.

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% and an enum restricts values, so the schema does the heavy lifting. The description still adds meaning by tying specific keys to effects (Tab moves to next field, Enter sends, Escape closes dialogs), which goes beyond the bare 'The key.' schema text.

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 (presses) and resource (one key on the current page in the Partiful Cloud Browser) and pins down the target (the focused element), which cleanly separates it from siblings like cotlet_browser_click and cotlet_browser_type.

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 when-to-use examples (Tab to next field, Enter to send, Escape to close, arrows for suggestion lists) and a notable exclusion (Enter is refused on account pages). It doesn't explicitly route to cotlet_browser_type for text entry, but the key examples make the boundary clear.

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