Choose how many tools are offered

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

No annotations are provided, so the description carries the behavioral burden fully. It discloses scope (rest of session), effect (tools hidden, not lost), environmental safety ('changes nothing in any environment'), the cost tradeoff being addressed (50k tokens of schema crowding smaller models), and a consent precondition. That is unusually complete for a zero-annotation tool.

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-loads the trigger and effect, then backs it with rationale and preset definitions. Information density is high, though the preset list and token-count rationale make it longer than strictly necessary; nothing is wasted but it could be tightened.

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?

There is no output schema and no annotations, so the description must cover purpose, scope, safety, and preset semantics – and it does. An agent has everything needed to decide whether to call it, which preset to pass, and that user confirmation is expected first.

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% and the enum values are documented in the schema, so the schema already carries parameter meaning. The description adds the semantics behind the preset names (what core/authoring/admin/solutions/full each contain), which is genuinely useful context beyond raw enum strings, but the 'keep' parameter is not addressed in the description at all.

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?

Names a specific action and resource (narrow/restore the tool list) with a clear motivating symptom ('too many tools'). Distinguishes itself from every sibling: it is the only tool that changes what tools are offered rather than operating on agents, flows, or environments.

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 the trigger condition explicitly ('Answer there are too many tools'), names the alternative direction (restore), and adds a process rule: 'Ask the user before calling it.' This is as close to explicit when/when-not as a session-scoped tool gets.

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