set_automation_profile

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

The description discloses non-obvious behavior beyond what annotations provide: the change is session-only ('does not persist or reload the extension') and BROWSERTAP_MODE takes over on the next process. This complements the idempotentHint and destructiveHint annotations without contradicting them.

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 with no filler: the first front-loads the action and resource, the second delivers the critical caveats about persistence and BROWSERTAP_MODE. Every clause earns its place.

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 one-parameter, session-scoped mutation with an output schema, the description covers purpose, scope, persistence, and the alternative mechanism. The main remaining gap is not explaining the behavioral differences between the 'safe' and 'lab' profiles, which matters given the destructiveHint annotation.

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 0% schema description coverage, the schema exposes only a bare 'mode' string, yet the description reveals the two intended values ('safe or lab'). It carries the parameter documentation burden, though the exact string format and validation behavior are left unspecified.

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 uses a specific verb ('Set') with a clear resource ('the safe or lab automation profile') and scopes it to 'this MCP process.' It states the two available mode values, which cleanly differentiates it from the sibling get_automation_profile.

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 clarifies that the effect is limited to the current process and does not persist or reload the extension, and that BROWSERTAP_MODE governs the next process. This gives an agent a clear boundary for when this tool applies, though it stops short of explicitly recommending an alternative tool for persistent configuration.

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