Get engagement signal

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

Annotations already declare readOnly/idempotent/non-destructive and closed-world, so the safety profile is covered. The description earns credit for disclosing the non-obvious semantics of the returned number: it derives from local interaction events with a 30-day half-life and explicitly is not live social-network engagement, which prevents a plausible misreading of the score.

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 tight sentences: what it returns, when to use it plus alternatives, then the caveat about what the score actually measures. The most decision-critical content (the return contents) leads, and no sentence is filler.

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?

With no output schema, the description usefully enumerates the returned fields, and the 30-day half-life note explains the value's meaning. Minor gap: it does not say what is returned for an item with no recorded events, so an agent cannot fully anticipate empty-state behavior.

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% and the video_id description already clarifies it is a stable saved-item identifier that may not be a YouTube ID. The description only implies 'one saved item' without adding identifier resolution rules, so baseline 3 is appropriate.

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 (read) and resource (one saved item's engagement signal) and enumerates exactly what comes back: time-decayed local score, event counts, last-event time. That precision separates it cleanly from analyze_self_channel and query_by_facets named in the same breath.

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?

Gives an explicit when ('assess how the user has used an item') and names two alternative tools with the conditions that select them ('captured channel-performance trends', 'stored performance labels'). The agent never has to infer routing.

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