bing_plan_add_deep_link_block

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

The description provides valuable insight beyond the annotations: it records intent only, actually sends nothing, and does not apply a real change. It explicitly tells the agent not to claim the change was applied. With annotations that only provide broad hints (readOnlyHint=false, destructiveHint=false), this description offers much needed clarification of the staged 'plan-by' nature of the 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?

The description is compact: three short sentences with no filler. The intent is front-loaded, the most important behavior is stated next, and the expected output is given a useful caveat. Every sentence carries essential information, and the structure supports quick model parsing.

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?

Despite strong conciseness, the description does not provide enough context for correct invocation. There are four required parameters with no parameter docs, no output schema, and a large family of bing_plan_* sibling tools. The description only clarifies the overall workflow, but impossible to know how to formulate the parameters or what exactly 'search_url' versus 'deep_link_url' mean.

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 zero parameter descriptions (coverage 0%) and the description contributes nothing to explain site_url, market, search_url, or deep_link_url. The agent is left to guess URL formats, what 'market' values are acceptable, and the relationship between search_url and deep_link_url. Since the description adds no semantic meaning for parameters, this is a critical gap.

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 communicates a high-level intent: prepare a change for human review, record intent, and return a plan id plus CLI apply command. However, it never explicitly names the deep-link block change being planned; 'Prepare this change' is ambiguous and requires the agent to infer from the tool name. It is not a tautology, but it lacks the explicit resource definition needed for a strong purpose statement.

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?

No usage conditions or alternatives are mentioned. There is no guidance about when to choose this tool over bing_plan_remove_deep_link_block or bing_deep_link_blocks. The instructions about not telling the user that the change was applied, and returning the plan id with the CLI command, are operationally relevant but are response behavior, not tool-selection guidance.

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