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

Beyond the annotations, the description discloses three non-obvious behaviors: it writes a fresh capture directory (explaining why readOnlyHint is false and idempotentHint is false), it reports individual artifact failures rather than failing atomically, and it caps log capture to the last five minutes / 100 lines. It does not say what happens if outputDir already exists or whether partial bundles are left on disk, which is the main remaining gap.

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 content is front-loaded with the artifact manifest and then constraints, with essentially no filler sentences. The only waste is the leading '# app-state-capture' heading, which merely restates the tool name and title.

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 three-parameter tool with no output schema, the description covers destination, optional filters, artifact inventory, partial-failure semantics, and truncation limits — enough to call it correctly. Missing are prerequisites (e.g., a booted simulator or connected device) and overwrite behavior for outputDir.

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?

With 0% schema description coverage, the description must carry all parameter meaning, and it largely does: udid is described as auto-detected (so the agent need not supply it), bundleId as an optional filter on recent logs, and outputDir as required for the capture destination. It never explains what outputDir is relative to or whether it must exist, so one semantic detail is left open.

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 ('Capture a diagnostic bundle') and enumerates exactly what the bundle contains (screenshot.png, accessibility.json, app-logs.txt, device.json, summary.json, README.md), which implicitly separates it from single-artifact siblings like screenshot or simctl-stream-logs. It stops short of naming a sibling or stating an explicit contrast, so it is clear but not fully differentiated.

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?

Usage context is only implied: the artifact list suggests post-failure or diagnostic triage, and the note that udid is auto-detected tells the agent it can omit it. There is no explicit when-to-use statement, no when-not guidance, and no pointer to alternatives such as simctl-stream-logs for raw log capture.

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