start_grab_session

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

Annotations already mark destructiveHint=true, so the description need not reiterate destructiveness. It adds context about starting a local server and injecting an overlay, but does not explain side effects like cleanup or what precisely is destroyed, leaving some behavioral gaps.

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, no wasted words. First sentence states purpose, second explains modes. Well front-loaded and efficient.

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 tool has 4 conditional parameters, a destructive annotation, and no output schema. The description does not explain what 'grab bridge' means, the role parameter difference, or what the return value is (e.g., session ID). This leaves significant gaps for an agent to use correctly.

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 100%, so the description adds minimal value beyond the schema. It reinforces the relationship between proxy_target and the preferred mode, but does not provide new syntax or format details.

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 uses the specific verb 'start' and names the resource 'Raven grab bridge on loopback'. It distinguishes from sibling tools like stop_grab_session (stop) and get_grabbed_elements (retrieve). However, the jargon 'Raven grab bridge' may be unclear to some agents.

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 states proxy mode is the 'preferred zero-paste path' and explains the two modes (proxy vs manual script tag), giving usage context. However, it does not explicitly compare to alternatives like stop_grab_session or mention when to choose this tool over others.

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