firefox_point

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

Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuinely non-obvious behavior: the screenshot is consumed and must be re-captured, and frames are not entered automatically. It omits what happens on a failed hit (error vs. silent no-op) and whether the action waits for load.

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?

Three short sentences, front-loaded with the capability and followed by the two constraints that most affect correct use. No filler; slightly terse given the number of undocumented parameters, but nothing is wasted.

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?

With five required parameters, 20% schema coverage and no output schema, the definition covers the core interaction model well but leaves tabId meaning and failure/return behavior unexplained. An agent could invoke it correctly in the happy path but would not know how errors surface or what the call returns.

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 description coverage is only 20% (just screenshotId), so the description has to carry more weight. It does enumerate the action variants in prose and ties x/y to a screenshot's coordinate space, but tabId is undocumented in both places and the relationship between screenshotId and its producing tool is only hinted at ('recent screenshot').

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?

Names the specific operations (click, double-click, hover, context menu) and the precise target (coordinates from a recent screenshot), which cleanly separates it from element-based siblings like firefox_click. It stops short of naming that sibling explicitly, so an agent must infer the distinction from 'at coordinates'.

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?

'Coordinates from a recent screenshot' plus 'capture again after changes' implies the intended workflow (screenshot → point → re-screenshot), and 'Does not enter frames automatically' rules out a case. However, no alternative tool is named and there is no explicit when-not guidance such as using firefox_click for element selectors.

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