desktop-touch-mcp

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behavioral traits: what the tool extracts (SSR-injected state only), what it returns (parsed payloads with framework labels), performance characteristics ('in one CDP call'), and important limitations/caveats ('client-only runtime state requires browser_eval'). It doesn't mention error handling or authentication needs, but covers the essential operational behavior.

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 efficiently structured with three sentences that each serve distinct purposes: stating the core functionality, providing usage guidance, and explaining limitations. It's front-loaded with the primary purpose, avoids redundancy, and every sentence adds value without unnecessary elaboration.

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 5 parameters, 100% schema coverage, but no output schema or annotations, the description provides good contextual completeness. It explains what the tool does, when to use it, its limitations, and how it relates to other tools. The main gap is the lack of information about return values (no output schema), but the description does mention what gets returned ('parsed payloads with framework labels'), which partially compensates.

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?

With 100% schema description coverage, the baseline is 3. The description adds minimal parameter semantics beyond what's in the schema - it mentions 'pass selectors to target specific window globals' which aligns with the schema's description of the selectors parameter, but doesn't provide additional context about parameter interactions or usage patterns that aren't already documented in the schema.

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 clearly states the tool's purpose with specific verbs ('extract', 'returns') and resources ('embedded SPA framework state', 'parsed payloads with framework labels'). It explicitly distinguishes from siblings like browser_eval and browser_get_dom by specifying when to use this tool instead ('use BEFORE... on SPAs where rendered HTML is sparse').

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 provides explicit guidance on when to use this tool ('use BEFORE browser_eval or browser_get_dom on SPAs where rendered HTML is sparse') and when not to use it ('Only extracts SSR-injected state — client-only runtime state requires browser_eval'). It names specific alternative tools (browser_eval) for different scenarios, offering clear decision criteria.

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