bing_plan_add_blocked_url

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

This is a strong disclosure of behavioral intent: it sends nothing, only records intent, and should not be reported as applied. These details go well beyond the annotations by explicitly describing the side-effect boundary and the desired agent-facing output behavior.

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, purposeful sentences with the most important behavioral distinction ('sends nothing and only records intent') front-loaded. No words are wasted and every sentence carries operational meaning.

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 covers the workflow well: what the tool does, what it does not do, and what to return. It is still incomplete because the nested blocked_url parameter is entirely opaque and the description does not clarify the relationship between the two required parameters or the expected shape of blocked_url.

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 description adds nothing about site_url or blocked_url. Worse, blocked_url is described only as an object, with no nested properties, so the agent has no help understanding what values it should construct or send.

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 that the tool stages a change for human approval rather than executing it, and it spells out the expected response artifacts: a plan id and a CLI apply command. However, it refers to 'this change' instead of explicitly saying that the change is adding a blocked URL to a site, leaving the resource vague outside of the tool name.

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 clear context about when to use this tool: use it to record intent for a future change, not to make an actual live change. It also warns the agent not to tell the user the change was applied. It does not enumerate alternative tools like bing_plan_remove_blocked_url, but the usage mode is clear enough.

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