bing_plan_remove_page_preview_block

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

The description adds useful behavioral detail beyond the annotations: it says the tool sends nothing, only records intent, and tells the agent not to tell the user that the change was applied. These details correctly convey that the tool is a planning stage rather than a mutating or destructive action, with no contradiction of the annotations.

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 short and front-loaded: two sentences that immediately say it is a review-stage tool and what to return. There is slight redundancy between 'only records intent' and 'do not tell the user the change was applied', but overall it is efficient.

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?

The description captures the critical plan/apply semantics and mentions the return values (plan id and CLI apply command), but it omits parameter behavior entirely and provides no description though the schema yields no help either. An agent has enough high-level context but not enough low-level detail for correct invocation.

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 description coverage is 0%, so the description has a much higher burden to explain 'site_url' and 'url'. It never mentions them, nor does it explain which URL is which or the expected formats. The agent is left without any parameter semantics beyond raw names.

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 communicates this is a planning/staging step, not an applied change, via 'prepare this change for human review' and 'records intent.' However, the phrase 'this change' is generic and only becomes meaningful when the tool name is read, so the concrete resource (removing a page preview block) is not actually described.

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 gives a clear usage context: this is for human review, it sends nothing, and the agent should not claim the change was applied. It does not name alternative sibling tools or provide an exhaustive when-not-to-use list, but it clearly communicates the plan-then-apply workflow and return behaviour.

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