bing_plan_remove_site

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

This is the key strength: it explicitly discloses that the tool 'sends nothing and only records intent,' preventing the agent from misleadingly telling the user the change has already been applied. It also directs return-quality behavior, which is more than the sparse annotations provide. There is no contradiction with 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?

Two short and direct sentences, front-loaded with the most important behavioral constraint ('sends nothing') before giving the expected response behavior. Every word earns its place and there is no wasted text.

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 a simple one-parameter plan-staging tool and no output schema, the description covers the crucial post-conditions: it does not apply, and the agent must return a plan id plus the apply command. It is nearly complete, though the parameter's meaning is left entirely to the schema-less name, so a small completeness gap remains.

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 description adds no meaning for the only parameter, site_url; it does not explain the format, what should be provided, or how it is used. Schema description coverage is 0%, so the description must compensate, but it does not. The parameter is inferable from the tool's name and context, but the description itself offers no guidance.

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 uses a specific verb ('prepare') and clearly identifies the tool's role as staging a change for human review rather than applying it. While it never explicitly names the resource ('site removal'), the tool name conveys that, and the 'sends nothing / records intent' line clearly distinguishes it from applying sibling tools.

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 sets clear context: use this when a change should be reviewed by a human, not confidently claimed as applied. It also instructs the agent to return a plan id and CLI apply command, which is exactly the expected workflow. It does not name an alternative tool or state a when-not-to-use, so it misses an explicit exclusion.

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