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

Annotations already declare idempotentHint=true and destructiveHint=true; the description adds real context on top by stating that omitting revisionId silently selects the newest accessible revision, that only user-owned strategies are valid targets, and that no files are copied. What it does not address is the destructive side effect an agent most needs to know about: whether the previously active workspace's state is lost or recoverable after the switch.

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 core action and the use-only-when gate are front-loaded, and each sentence carries distinct information. The middle section on named-target precedence is dense but slightly repetitive around 'the user is actually moving the workspace target', costing a little tightness.

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 zero-required-parameter state-mutation tool with no output schema, the description covers ownership scope, default revision selection, non-copying behavior, and sibling routing, which is most of what an agent needs. The remaining gap is post-switch semantics — what happens to the prior workspace and whether the switch is reversible — which matters given destructiveHint=true.

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 all three parameters (revisionId, strategyId, aiStrategyId) are already documented, including the 'omit revisionId for newest revision' guidance. The description restates the revisionId default and adds only a high-level resolution workflow, which is also present in the schema's parameter descriptions — baseline 3 is appropriate.

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 with scope: 'Changes this conversation's active strategy workspace to another strategy owned by the user.' It explicitly contrasts with the nearest-confusable behaviors, noting it 'does not copy files by itself' (vs. clone_strategy/file tools) and that it repoints the workspace rather than editing a revision (vs. set_strategy_revision).

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?

Gives an explicit gating condition ('Use only when the user explicitly asks to work with, compare against, copy from, or move to a different strategy') plus a tie-break rule: an explicitly named owned strategy beats the currently open page/context. It also routes to the resolution path (list_strategies / named target first) and names the follow-on tools (file tools) for the copy case.

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