snapshot_integrity_report

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

No annotations exist, so the description carries the full behavioral burden. It does disclose the report's scope (all local snapshots), the file-level valid/corrupt check, and the playlist-coverage and age axes, which usefully implies the tool scans snapshot storage. However, it never explicitly states the operation is read-only, what 'corrupt' means or how validation is performed, or that aggregating over all snapshots may incur noticeable cost.

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?

A single front-loaded sentence that opens with the core concept ('Aggregate health report over all local snapshots') before spelling out the three report axes after a colon. Every word earns its place and there is no filler, though cramming three axes into one sentence makes it somewhat dense to parse.

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?

The three listed axes partially compensate for the missing output schema by conveying what the report will contain, and the one parameter is fully schema-documented. But the definition omits edge cases (e.g., behavior when no snapshots exist), how 'corrupt' is determinated, whether it reads the filesystem versus a registry, and performance implications — all relevant for an aggregate tool scanning every local snapshot.

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 single optional response_format parameter is fully documented in the schema ('concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object). The description contributes nothing about parameters, which is acceptable at this coverage level, so the baseline 3 applies.

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 action ('aggregate health report') over a specific resource ('all local snapshots') and enumerates three concrete report axes: valid vs corrupt files, per-playlist coverage, and age of each playlist's newest snapshot. 'Aggregate' and 'over all local snapshots' imply a scope distinction from per-snapshot siblings like snapshot_integrity_check, but that contrast is never made explicit. Clear and specific, with sibling differentiation left mostly implicit.

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?

Provides no guidance whatsoever on when to select this tool over the many adjacent snapshot tools in the sibling set (snapshot_integrity_check, snapshot_stats_report, snapshot_registry_report, snapshot_disk_usage). No trigger conditions, no exclusions, no alternatives — the agent must infer selection from the name and content list alone.

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