figma_watch_console

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

With no annotations, the description carries the full burden and does well: it discloses the hard 5-minute cap, the plugin-scope limitation, and that the call returns all captured logs plus summary statistics. It stops short of stating that the call blocks for the full duration (an important behavioral fact for an agent's planning) and says nothing about cancellation or behavior if the plugin is not connected.

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?

Front-loaded with the core action and duration limit, then scope, then return shape, then exclusions — a sensible priority order. It is slightly dense with four distinct ideas packed in, but no sentence is filler and the 'Best for:' tail genuinely helps routing.

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?

No output schema exists, and the description compensates by describing what comes back ('all logs captured during the watch period with summary statistics'). Both parameters are documented, the duration cap is stated, and the scope boundary is drawn — nothing an agent needs to invoke this correctly is missing.

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 100%, so baseline is 3; the description earns above baseline by adding the 'max 5 minutes' ceiling that the schema's 'How long to watch in seconds' field does not state. The 'level' enum filter is left entirely to the schema, which is acceptable given full coverage.

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 ('stream') and resource ('console logs captured by the Desktop Bridge plugin') plus the temporal scope ('real-time for a specified duration'). It explicitly delimits what is in scope (figma_execute and write tools) versus out of scope (other plugins' sandboxes), which lets an agent distinguish it from figma_get_console_logs without opening either 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?

Provides an explicit negative case — 'NOT for retrieving past logs (use figma_get_console_logs)' — naming the sibling and the condition that selects it. The 'Best for:' clause adds concrete scenarios (long-running scripts, race conditions, async operations) that make the when-to-use decision unambiguous.

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