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

Annotations declare readOnlyHint=true and destructiveHint=false, so safety is already partly covered, but the description adds substantial non-structured context: that invoking it injects a Skill into the conversation and alters agent working behavior, and that it never weakens safety or required confirmations. What remains unstated is persistence — whether the mode lasts for the rest of the conversation or a single goal.

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?

Three sentences, front-loaded with the gating condition before the behavioral explanation. Every clause carries information — trigger, mechanism, effects, safety reassurance — with no filler or repetition of the title.

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 need not be described, and with zero parameters the surface is small. The description covers trigger, mechanism, and effects, but leaves the duration/exit semantics of the mode ambiguous, which matters for a session-behavior switch.

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?

The tool takes zero parameters and the schema is empty, so there is nothing for the description to disambiguate at the parameter level. Baseline 4 applies for a no-argument tool.

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 action (loads the execution-governor Skill into the current conversation) and enumerates the concrete behavioral effects: goal prioritization, scope-creep limits, risk-based validation, and stopping at the Definition of Done. An agent knows exactly what enabling this mode changes, and no sibling tool operates on this concept.

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 first sentence gives an explicit and narrow trigger: only when the user explicitly asks to enable, use, or enter high performance mode. That effectively rules out proactive invocation. It does not name an alternative or explain how to leave the mode, but no sibling tool offers comparable functionality, so there is nothing to route away from.

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