check_delivery

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

With no annotations, the description carries the full burden and does so: it declares read-only semantics, that files are hashed and never imported or executed, that contents are not returned, and it distinguishes hard failures from warnings. That is exactly the safety and outcome profile an agent needs before invoking an artifact-inspection tool on shipping output.

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 dense sentences, front-loaded with what the tool checks, then how to enable the full check, then the safety profile. Every clause carries information, though the middle sentence is heavily comma-loaded and could be marginally tighter.

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 described, and the description covers purpose, trigger timing, optional inputs and safety. The remaining gap is behavior when the optional report/manifest is absent or malformed, which matters for a gating pre-ship check.

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 coverage is 0%, so the description must compensate, and it largely does: 'path' is clarified as an output directory or a .whl, and build_report / provenance_manifest are tied to the build's --build-report and --provenance-manifest JSON artifacts. It stops short of specifying whether these are file paths or inline JSON, and any format expectations.

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?

Specific verb (check) plus resource (output directory or .whl) with an explicit temporal scope ('right before shipping') and concrete failure/warning conditions (pyobfus mapping file, private key, original source, unreported Python files, skipped Pro options). This distinguishes it from the adjacent pre-build sibling check_obfuscation_risks, which audits risks rather than validating a finished artifact.

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?

States when to use it ('right before shipping') and how to get the most out of it ('Pass the build's --build-report and --provenance-manifest JSON for the full check'), implying the no-report path is a degraded check. It does not name an alternative tool or an explicit when-not-to-use, so it falls short of a 5.

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