annotation_mode

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

With no annotations provided, the description carries the full burden. It usefully discloses the key behavioral trait that annotations arrive as a structured text message, but omits persistence/scope behavior (per-tab only? survives navigation?), the default state, and whether tabId is optional or defaults to the active tab.

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 tight sentences: the action is front-loaded and the second sentence explains the payoff of the mode. No filler, no repetition of 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?

For a tool with no annotations and no output schema, the description explains the input side (what the human will do) but not the mechanics an agent needs to call it correctly: tabId optionality, mode lifetime, and whether annotations interrupt or arrive asynchronously. Adequate but with clear gaps.

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 50%: the schema documents 'active' (true = enter, false = exit) but leaves 'tabId' unexplained. The description only hints at tabId via 'on a tab' and never clarifies whether it is optional or defaults to the current tab, so it only marginally compensates for the coverage gap.

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 and resource ('turn the human annotation mode on/off on a tab') and then describes the concrete effect of the mode — human draws shapes or picks an element and attaches a question. This is clearly distinguishable from every sibling (screenshot, click, evaluate) without opening 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 implies the usage context (enable it so the human can send you structured annotation messages) but never states when to enable vs. leave off, whether it should be toggled off after receiving input, or any alternative for obtaining human feedback. Guidance is inferable but not explicit.

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