squire

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

No annotations are present, so the description must carry the full burden. It disclose the side effect of downloading artifacts locally and mentions 'clean environments,' but omits critical behavioral details: whether the operation is destructive to local files, environment lifecycle/cleanup, authentication requirements, or what the return value/response contains.

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?

Single, well-structured sentence (20 words) that is front-loaded with the core action. Every clause earns its place: 'offline packaging' defines mode, 'build sanity checks' defines purpose, 'clean environments' defines isolation, and 'optionally pull... locally' defines the download behavior. No redundancy.

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?

Given 100% schema coverage, the description appropriately focuses on workflow intent rather than repeating parameter definitions. However, with no output schema provided, the description should ideally explain what success returns (e.g., build logs, artifact locations, status), which it omits. Adequate but has a clear gap in return value documentation.

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%, establishing a baseline of 3. The description adds conceptual context for 'download_artifacts_dir' by mentioning pulling artifacts back locally, and implies staging via the build context, but does not augment the schema's descriptions of 'targets,' 'timeout,' or the specific semantics of the staging parameters.

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?

Clearly states the action ('Run offline packaging and build sanity checks') and context ('clean environments'), plus the optional artifact retrieval. However, it does not explicitly distinguish from the 'compile' sibling tool, which may also perform build operations.

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 implicit context through terms like 'offline' and 'clean environments' suggesting isolated builds, but lacks explicit guidance on when to use this versus 'compile' or other build-related siblings, and omits prerequisites or exclusion criteria.

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