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

Annotations already declare destructiveHint=true and idempotentHint=true, and the description adds meaningful context: it lowers the user's score and requires confirmation before removing unrequested items. This goes beyond the annotations by explaining the consequence of the action. It doesn't contradict 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?

Three sentences with no fluff. The core action is front-loaded, the input format is stated, and the caution is placed at the end. Every sentence earns its place.

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 single-parameter tool with no output schema, the description covers the action, input format, and a key side effect (score decrease). It doesn't describe the return value, but with no output schema and a simple action, that's a minor gap. The confirmation warning adds important context for safe use.

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 coverage is 100%, so the schema already documents the single 'place' parameter. The description adds the useful detail that the value can be either a place id or an exact name, which is a slight enhancement over the schema's 'A place id, or its exact name.' Since the schema already covers this, the description adds minimal extra value, warranting a baseline 3.

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 states the verb 'Unmark' and the resource 'a specific place such as a monument, museum, airport or city', and explicitly frames it as undoing add_place. This distinguishes it from sibling tools like remove_country and remove_region, which target different resource types.

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 explicitly says it accepts a place id from search_places or the exact place name, which tells the agent how to obtain the input. It also warns to confirm before removing anything the user did not name, providing a clear when-to-use caution. It doesn't explicitly name alternatives, but the 'undoing add_place' phrasing and the sibling list make the relationship clear.

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