bing_plan_save_crawl_settings

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

The description usefully discloses the main behavioral subtlety: the tool does not apply the change, only records it. It also tells the agent not to claim the change was applied and to return the plan id and CLI apply command instead. This is valuable beyond the annotations because it prevents a misleading success message.

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 description is three short sentences with no filler. It front-loads the core purpose, then gives the most important behavioral warning, then states the expected response. Every sentence contributes useful information.

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?

Given there is no output schema, the description wisely explains exactly what the agent will receive: the plan id and the CLI apply command. It also covers the key side-effect boundary. It is less complete in explaining how crawl_settings should be structured or when this plan tool should be selected over the other plan/crawl sibling tools.

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 schema has 0% description coverage and the tool description adds no parameter-level meaning. site_url is self-explanatory, but crawl_settings is an unspecified nested object whose content and shape are completely undocumented. The description needed to bridge that gap and does not.

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 clearly states that this tool prepares a change for human review and only records intent rather than applying the change. It is somewhat generic—"this change" is not explicitly tied to crawl settings in the text—but the tool name and parameters fill in the resource. It does distinguish itself from likely execution-style tools by emphasizing that nothing is sent.

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 phrase 'Prepare this change for human review' implies the intended use case, but the description gives no explicit guidance about when to choose this tool versus bing_crawl_settings or other bing_plan_* alternatives. The instruction about returning a plan id and CLI apply command gives some operational context, but the “when vs. alternatives” guidance remains implicit.

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