Anchor the exact TV UI state by naming page, focus, keyboard, and modal after inspecting a recent screenshot, since a selected tab alone is insufficient.
Name exact page, focus, keyboard and modal state after inspecting a screenshot taken within 30 seconds. Selected tab alone is insufficient. Context expires after 60 seconds or an untracked command/reconnect.
| Name | Required | Description | Default |
|---|---|---|---|
| state | Yes | ||
| witness_id | Yes |
Changes observed during successful MCP inspections.
v0.3.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the behavioral burden. It discloses important timing and invalidation behavior, including the 30-second screenshot freshness requirement and 60-second context expiration, but it does not state side effects, permissions, return behavior, or error conditions.
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 three tight sentences, front-loading the purpose and then adding essential constraints. Every sentence carries useful information without repetition or filler.
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 two-parameter tool with no annotations, no output schema, and 0% schema description coverage, the description is incomplete. It covers timing and invalidation well but omits the meaning of witness_id, side effects, and what the agent can expect after anchoring state.
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 0%, so the description must explain both parameters. It indirectly describes what the state parameter should contain (page, focus, keyboard, modal state), but witness_id is never mentioned or explained, leaving a required parameter completely opaque.
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 gives a specific verb ("Name") and the exact UI state fields to capture: page, focus, keyboard, and modal state. It also clarifies that selected tab information alone is insufficient, which helps distinguish it from simpler state-reading siblings, though no sibling tool is explicitly named.
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?
It clearly states the required context: use after inspecting a screenshot taken within 30 seconds, and when selected tab alone is insufficient. It also gives expiration conditions (60 seconds or untracked command/reconnect), which tells the agent when the anchor is no longer valid.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.