computer

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

With no annotations, the description carries the burden of behavioral disclosure. It reveals that operations are coordinate-driven and require screenshots for positioning, as seen in the bullet about consulting a screenshot before clicking. It also hints at potential failure and recovery ('try adjusting your click location'). This is useful context, but it doesn't cover other behavioral aspects like how failed actions are returned, whether actions are asynchronous, or any side effects.

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?

The description is appropriately concise, with a high-level opening sentence followed by three focused bullet points that provide actionable tips. Each sentence earns its place, and the structure makes it easy to scan. It avoids redundancy with the 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?

Given the tool's complexity (12 parameters, many actions, broad capabilities), the description provides a reasonable overview but leaves several aspects implied rather than explicit. It covers the core interaction pattern and prerequisite (tab ID), but doesn't discuss how to choose among actions or handle different scenarios. The presence of an output schema reduces the need to explain return values, so completeness is adequate but not rich.

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 parameters are already well-documented in the schema. The description adds minimal extra parameter meaning beyond reinforcing the use of tabs_context for tabId and the need for coordinates when clicking. The baseline of 3 applies because the schema does the heavy lifting; the description doesn't need to compensate and doesn't add substantial value.

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 tool's role: using a mouse and keyboard to interact with a web browser and take screenshots. It distinguishes itself from sibling tools like navigate or read_page by focusing on low-level input actions. However, it could be more explicit about the set of actions (click, type, scroll) rather than relying on the 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?

The description provides some guidance on when to use the tool, especially related to handling tab IDs: 'If you don't have a valid tab ID, use tabs_context first'. It also gives practical tips for click accuracy (consulting screenshots, adjusting click position, clicking centers). However, it doesn't explicitly compare to alternatives like act_on or form_fill, so the 'when vs alternatives' aspect is only partially addressed.

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