capture_debug_snapshot

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

With no annotations, the description carries the full burden and does substantial work: it names the return fields (snapshot_revision, captured_at_ms, snapshot_delta, loading_state), discloses evidence metadata with acquisition intervals and conservative freshness, and warns that device log times are not comparable with host dispatch times. It still omits whether the call is strictly read-only, whether screenshot collection is expensive/slow, and what happens when no device is attached.

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?

The core purpose is front-loaded in the first clause and the remaining sentences each carry distinct payload (return shape, freshness semantics, actionRef behavior, clock-domain caveat). It is dense but not padded, though the return-field enumeration is compact enough to border on terse for a reader unfamiliar with the payload.

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 9-parameter tool with a nested object and no output schema, the description usefully explains the return shape and the freshness/clock caveats an agent would otherwise have to guess. The main remaining hole is usage routing against the sibling observation tools, which the description never addresses.

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 89%, so the schema already documents appId, deviceId, logLines, includeLogs, includeScreenshot, platform, and sessionId. The description adds real meaning only for actionRef (same-session/device linkage, independent collection for unavailable references), which is the one undocumented nested parameter — helpful but narrow, so baseline-plus-one is not warranted.

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 opens with a specific verb and resource — 'Capture a complete debug snapshot (raw observation layer plus optional derived semantic layer)' — which tells an agent exactly what is produced. It does not, however, differentiate itself from close siblings such as get_logs, capture_screenshot, or get_ui_tree, which overlap with the raw/derived layers it mentions.

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?

There is no statement of when to reach for this tool versus the many sibling observation tools (get_logs, capture_screenshot, get_ui_tree), nor any prerequisites or exclusions. The only situational guidance is a narrow note that actionRef links a known same-session/device action, which is a parameter detail rather than usage routing.

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