tv_ui_metadata

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

Annotations declare readOnlyHint=false with destructiveHint=false, and the description usefully explains the apparent inconsistency: the tool creates a temporary dump and removes the remote file afterwards, which is why it isn't read-only. That is genuine added context. However, it omits cost/latency of a dump, whether concurrent calls conflict on the temp file, and what happens if removal fails.

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?

One sentence, front-loaded with the action and its resource, with no filler. It is dense enough that the temp-file lifecycle clause reads slightly compressed, 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?

An output schema exists, so return values needn't be described. Still, for a tool that mutates remote state via a temp file and sits among nine TV siblings, the definition should explain when to reach for it and any limits on repeated calls. Adequate but incomplete.

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 0% with one parameter, max_nodes, whose bounds (1-200, default 80) appear only as raw constraints. The word 'bounded' hints that node count is capped but gives no guidance on choosing a value or what you lose at low values. Minimal compensation for an undocumented parameter.

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: reads accessibility nodes, bounded, via a temporary UI dump that is then deleted. An agent can tell this apart from tv_status or tv_navigate because it explicitly concerns UI node data. It stops short of saying what the nodes represent (screen hierarchy) or how they relate to siblings.

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?

No when-to-use guidance at all: it never says to call this before tv_text/tv_navigate to locate elements, nor when tv_status would be a cheaper alternative among the nine siblings. The use case is only inferable from the phrase 'accessibility nodes'.

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