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

Beyond the annotations (destructive, idempotent), the description discloses the budget-consumption rule and its exception, which is not otherwise visible from annotations or schema. It also explains the anti-cycling rationale and the policy guardrails around mass-unstarring.

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 front-loaded with the core action and then presents structured warnings. It is longer than a minimal description, but each sentence carries policy or cost information that materially affects invocation. Minor redundancy could be tightened.

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 destructive tool with a single parameter and no output schema, the description covers the prerequisite call, the cost model, the exception, and policy guardrails. The agent has everything needed to correctly decide whether and how to invoke it.

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 input schema already documents listingId with a clear description and 100% coverage, so the description doesn't need to add parameter-level detail. The phrase 'company listing' aligns with the parameter but introduces no additional semantic info.

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 states a specific verb and resource ('Remove a star from a company listing') and is clearly the inverse of the sibling star_listing. It is unambiguous and distinguishable from the other save/delete 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?

It explicitly instructs the agent to call get_account first, defines the only acceptable reason to unstar, and forbids mass-unstarring without explicit user consent. It also specifies how to handle the over-cap case: surface the choice and let the user decide.

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