playback_health_check

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

No annotations are provided, so the description carries the full behavioral burden — and it delivers with the explicit 'Read-only' disclosure and the 'reporting pass/fail per probe' output contract. This tells the agent both that no state mutation occurs (matching its diagnostic nature) and how results are surfaced, which is especially valuable for a probe tool that would otherwise be ambiguous about failure handling.

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?

Two sentences, zero waste. The verb 'Probe' is front-loaded, the four checks are compactly listed in a single clause, and the critical behavioral note ('Read-only') is isolated at the end where it is easy to parse. Every segment earns its place.

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 simple read-only tool (1 optional param, no required params, no output schema), the description is nearly complete: it covers scope, the specific probes performed, the output format, and side effects. The only notable absence is competitor routing to the many adjacent diagnostic tools, but that gap is already accounted for in usage_guidelines, and the pass/fail output description compensates for the missing output schema.

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 description coverage is 100% — the response_format parameter is fully documented with enum values and per-value explanations (concise/detailed/json). The description's 'pass/fail per probe' framing adds useful context about what the underlying report contains, which helps an agent interpret what 'concise' versus 'detailed' would render, but this is marginal enrichment over an already-complete schema.

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 ('Probe') with a specific resource ('the playback stack end to end'), then enumerates exactly what is checked: token validity, available devices, current playback state, and queue readability. This makes it clearly distinguishable from overlapping health tools like playlist_health_check, device_health, and quota_probe without needing to open any schema.

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 purpose strongly implies usage — this is the diagnostic to run when checking playback stack health. However, with dozens of adjacent diagnostic tools (spotify_doctor, device_health, get_playback_snapshot, get_context_inspect), there is no explicit statement of when to choose this tool over those alternatives, nor any when-not-to-use guidance.

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