bing_plan_add_query_parameter

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

Annotations provide only readOnlyHint=false with no meaningful idempotency/state info, so the description does the important work: it states that 'This sends nothing and only records intent' and that the tool does not actually apply the change. It also specifies the exact response behavior—return the plan id and CLI apply command, do not tell the user the change was applied. This goes well beyond because bool flags and clarifies the mutation is a non-applying plan. It is not a 5 because it omits whether the plan must be approved and what happens if the same parameter already exists.

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 only three sentences, with the most decision-relevant facts front-loaded: prepare for review, record only intent, and return plan id plus CLI command. Every sentence conveys a usable instruction. The minor drawback is that 'this change' is ambiguous without fitting the tool name.

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?

For a tool with only two string parameters and no output schema, the description covers the essential workflow, return expectation, and what not to tell the user. It does not explain what 'CLI apply command' refers to as the tool output, and 0% schema coverage leaves both parameters semantic gaps, but the description itself covers the core invocation contract.

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% and the description says nothing about 'site_url' or 'query_parameter' meaning, format, or conventions. Both parameters are only plain strings, so the agent can guess 'site_url' is the website, but 'query_parameter' is ambiguous (is it just a name, or 'key=value'? Should it include '?'? ). The description fails to compensate for the empty schema.

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 says it 'records intent' for a change and returns a plan id plus a CLI apply command, so it clearly signals this is a planning/recording action rather than a live mutation. The tool name supplies the resource, add a query parameter, and the description differentiates it from direct-action tools by stressing that it 'only records intent'. However, it never explicitly says 'add query parameter to a site' and relies on the tool name for the exact resource, so it is not a perfect 5.

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 workflow context: prepare the change for human review, do not tell the user the change was applied, return the plan id and apply command. This implies when to use it versus actually applying a change. But it never names any alternative tool (such as a direct add or a remove counterpart), nor does it explicitly say 'use when the user needs human review before the change is applied', so the routing is left implied.

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