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

The annotations already state that this is not a read-only and not a destructive operation; the description does add useful behavior by explaining how to undo it (DELETE) and how repeat calls are counted. However, "Calling again does not add up: the counter counts people" reads as an idempotent effect, which is in tension with idempotentHint=false, and the description never resolves the ambiguity: does a repeat call error, return the same state, or silently no-op? The one-sentence behavioral summary is therefore too thin and slightly contradictory for a state-changing 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?

Two short sentences, front-loaded with the action and the undo path, with no wasted framing. The second sentence is compact but phrased cryptically ("the counter counts people"), which costs a little clarity even though the overall length is right.

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?

The tool is simple (2 required parameters, 100% schema coverage, no output schema), so the description does not need to explain the return shape. Still, for a like operation, it leaves open what the response conveys (like count vs. like status), how a repeat call behaves, and whether authentication failures are common; these gaps are tolerable but real.

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 100%, so both id and guest_token are already documented in the schema, including how the token is sent and reused. The description adds no parameter-level meaning beyond that, so the baseline score of 3 applies.

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?

States a specific verb and resource ("Likes the listing") plus the undo path ("DELETE undoes it"), so the agent knows exactly what action is performed. It does not name or contrast with any sibling tool, so an agent must infer on its own that there is no dedicated 'unlike' tool in this family.

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 implies usage through two hints: the DELETE reversal path and the note that repeat calls are harmless ("Calling again does not add up"). It never states prerequisites (e.g., that guest_token must come from create_guest), nor when to prefer this over adjacent tools such as watch_tool or go_listing; usage is only implied.

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