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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial behavior beyond that: the two-step fallback cascade, the response fields (requested_/effective fairness, threshold_relaxed, degraded), and the instruction to inform the user when their threshold was relaxed. That is exactly the kind of out-of-band behavior an agent cannot infer from structured fields.

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?

Four sentences, front-loaded with the purpose and then the fallback rules, with no obvious filler. It is dense but each sentence carries load; the only mild friction is the long parenthetical about scoring that could be tightened.

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?

For a complex nested-parameter tool with an output schema, the description covers the fallback mechanics and the key response signals (threshold_relaxed, degraded) that the agent must surface. It is nearly complete, with the only gap being the undocumented secondary parameters (limit, timeframe, include_streaming_xref).

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 29% across 7 parameters, so the description must compensate. It does define fairness semantics ('min(scoreA,scoreB) >= threshold — no veto') and the min_score halving behavior, but says nothing about limit, timeframe, include_streaming_xref, or the person_a/person_b preference fields, leaving most parameters undocumented.

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 with a distinguishing scope: 'Finds TV programs that satisfy two people with different moods/preferences.' This clearly separates it from single-user siblings like tv_recommend_by_mood or tv_concierge without needing to open 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?

The description defines the operative condition for the default (fairness=strict) and the exact fallback ladder when strict yields nothing, which is real when-to-use guidance. It never names an alternative sibling (e.g. tv_recommend_by_mood for solo requests) or states when NOT to use this tool, so it stops short of a 5.

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