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

Annotations already indicate non-read-only and non-destructive. The description adds useful behavior: it runs build_validate first unless force=true, and it returns artifact identifiers. This gives the agent a clear expectation of side effects without contradicting the annotations.

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 very concise, using compact symbols and a few sentences to cover the main action, return values, validation behavior, and the three file-providing options. No unnecessary filler or redundant repetition of schema details.

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 the tool's purpose, the description covers all critical aspects: what it does, what it returns, the validation flow, and the various input methods. It omits edge cases like error handling or prerequisites, but these are not essential for an agent to successfully invoke the tool.

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?

The schema already documents most parameters explicitly (files, force, app_type, validate, files_ref, files_b64gz), with project_uuid missing a description. The description adds extra context for files_ref and clarifies the file map format, which goes beyond the schema's existing notes.

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 clearly states the action: package, upload, and record a version under the project. It also mentions the return values (version_uuid, file_id, download_url) and the validation step, which distinguishes it from staging and deployment tools.

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 internal options (files, files_b64gz, files_ref) and when to prefer one over another, but it does not explicitly tell the agent when to use this tool versus siblings like build_stage_bundle or build_deploy. It only implies that this is the publish step.

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