deliver_screenshots_audit

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

No annotations are provided, so the description carries the full burden. It discloses the read-only nature ('No writes'), the comparison semantics (exactly the local files, in order, all COMPLETE, matching MD5), and that it lists preview sets. It does not detail auth needs or what happens on mismatch, but the behavioral profile is well described.

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?

Front-loaded with the core purpose, but the middle clause is densely packed and requires parsing around escaped quotes and parenthetical mappings. Three sentences is appropriate, yet the second sentence is information-dense and not optimally readable.

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?

An output schema exists, so return values need not be explained. The description covers the comparison contract, sequencing, and read-only guarantee for a 2-param tool. Minor gaps: no note on failure behavior when the audit finds mismatches.

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 0% for two required params (app_dir, bundle_id), so the description doesn't compensate. However, both parameter names are reasonably self-evident and the description's framing implies app_dir is the project directory whose local screenshots are compared. Baseline 3 given the shallow 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?

States a specific verb+resource: 'Read-only screenshot readiness audit' of the ASC screenshot set per locale/display type. It names exact display-type mappings (APP_IPHONE_67, APP_WATCH_ULTRA) and describes what it compares, distinguishing it clearly from deliver_screenshots (which writes) and screenshot_sync.

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?

Explicit sequencing: 'Run after deliver_screenshots and before submission.' This tells the agent precisely where this tool sits in the pipeline relative to a named sibling, leaving no ambiguity about when to invoke it.

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