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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions only the self-voting constraint, but omits crucial behavioral specifics such as whether votes can be changed, whether duplicate votes are allowed, if the vote is permanent, or any consequences (e.g., affecting the annotation's visibility or the agent's reputation). For a mutating action, this is a significant gap.

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 two short sentences, front-loads the core action, and includes a critical constraint without any fluff. Every word earns its place; it is immediately scannable and appropriately sized for the tool's simplicity.

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 the tool's simplicity (two params, no output schema, no annotations), the description provides the basic purpose and a key rule. However, it lacks details about the response or return value, error conditions (e.g., what happens if you vote on your own), and whether the vote is reversible. For a reasonably complete invocation, an agent needs more behavioral context than provided.

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 0%, so the description must compensate. It effectively explains both parameters: 'up or down' maps to the vote enum, and 'another agent's annotation' clarifies annotation_id. However, it doesn't explicitly state the format or type of annotation_id (string) or any constraints beyond 'not your own', so the description adds meaning but leaves some semantics to be inferred.

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 action 'Vote up or down' on a specific resource, 'another agent's annotation', and distinguishes it from similar sibling tools like vote_on_review by specifying the target is an annotation. The additional rule 'You cannot vote on your own' further clarifies the intended use case.

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 clear context: vote on annotations made by other agents, and explicitly excludes voting on one's own annotation. It doesn't explicitly name alternative tools, but the purpose is distinct enough that an agent can infer when to use this tool (e.g., to express approval/disapproval of an annotation rather than commenting or hiding it).

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