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

Annotations already declare non-read-only, non-destructive, non-idempotent behavior. The description adds important context beyond them: the "watched" tag is historical and does not create a follow, and dismiss/block/restore are action tools rather than this feedback tool. It does not clarify duplicate-feedback handling or reversibility, but that is a minor gap given annotations and the output schema.

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, front-loaded with the core purpose, followed by the most non-obvious caveat and the relevant alternatives. There is no redundant restatement of the schema or annotations.

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 rich schema, annotations, and output schema, the description covers the critical non-obvious behavior: watched feedback does not follow a company, and action tools are separate. A small ambiguity remains because the feedback_types enum includes "dismissed" while the description says dismiss actions are separate tools, so an agent may still need to infer whether recording that tag is distinct from recommendations.dismiss.

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 all three parameters and enumerates the feedback tags. The description adds meaning by clarifying the semantics of the "watched" tag and distinguishing it from the separate follow/action tools, though it does not explain every feedback tag or interaction_source.

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 uses a specific verb and resource: "Record recommendation feedback." It also distinguishes the tool from close siblings by naming following.follow and the separate dismiss/block/restore tools, so an agent can identify its scope without opening schemas.

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 gives explicit routing guidance: "Use following.follow first" for the watched case and "Dismiss/block/restore actions are separate tools." These are concrete when-to-use and when-not-to-use rules tied to named alternatives.

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