Past recommendations

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

The annotations already declare that the tool is read-only, idempotent, non-destructive, and open-world, so the safety profile is covered. The description adds useful context that the results are historical records paired with baselines. It does not disclose ordering, whether the history is bounded, or how 'limit' truncates the list, which are behaviors an agent would want to know.

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?

It is a single front-loaded sentence with no filler, and the purpose is stated before the use case. The parenthetical about baselines is efficient. It is slightly terse for a tool that has an undocumented parameter.

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?

An output schema exists, so the description does not need to explain return values, and the annotations cover safety. The remaining gaps are ordering, limit behavior, and channel scoping. For a simple two-parameter read tool, this is adequate but not complete.

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 only 50%: channel_id is documented in the schema, but limit is not documented beyond its numeric bounds. The description adds no meaning to either parameter; it says nothing about what limit counts, what order results come in, or that omitting channel_id falls back to the default connected channel. It therefore fails to compensate for the coverage gap.

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: retrieving recommendations that were made earlier, together with their baselines. This clearly separates it from the sibling youtube_recommend_publishing_time, which generates new recommendations rather than reading past ones. It does not explicitly name that sibling, but the phrase 'made earlier' makes the distinction clear.

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 the purpose of the tool through 'so you can check them against what happened next', which indicates that the tool is meant for retrospective review. However, it does not say when to use it versus alternatives, whether to call it before or after an analytics call, or what it excludes.

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