pack_solution

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

The description goes well beyond the annotations. It discloses that dry_run is the default and returns a plan/command plus warnings, that execution requires allow_writes=true (implying a write operation), that nothing is sent to an environment, and that the default output path is <output>/packs/. It also mentions specific warnings (canvas data sources Studio would prune, empty DatabaseReferences). These are valuable behavioral insights not present in the annotations, and there is no contradiction.

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 description is three sentences, with the core purpose front-loaded and every sentence adding new information. No fluff, no repetition. It packs a lot of relevant detail into a compact form, making it efficient for an agent to parse.

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 tool with 5 parameters and no output schema, the description covers the critical aspects: the local-only nature, the dry_run default and its return value, the need for allow_writes, the default output location, and even warning types. It does not explain the return value for actual execution (only for dry_run) and leaves package_type and overwrite behavior undocumented. These are secondary, so the description is quite complete but not perfect.

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%, so the description must compensate. It does explain dry_run in detail and indirectly mentions zip_path via the default output location. However, it does not explain the remaining parameters: folder (though obvious from context), overwrite, and package_type. The package_type default 'Unmanaged' and the meaning of overwrite are left undocumented. Given the 0% coverage, this is a moderate gap; the description adds some meaning but not enough for a fully informed call.

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 starts with a specific verb-resource pair ('Pack an unpacked solution folder into a solution zip') and names the underlying command (pac solution pack). It also distinguishes the tool from environment-touching siblings by stating 'Local only: nothing is sent to an environment.' This is clear, distinct, and immediately actionable.

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?

The description explains the primary use case (packing locally) and the dry_run behavior, which implies when to use dry_run vs actual execution ('dry_run=true (default) returns the plan...'). It does not explicitly name alternatives (e.g., export_solution, import_solution) or state when not to use this tool, but the local-only constraint and the pack/unpack pairing with unpack_solution provide enough context. A slight deduction for not explicitly routing to a sibling when appropriate.

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