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

Goes well beyond the annotations: it discloses the exact validation rules (at least one addon or manifest, parents resolve, no plaintext secrets), the secret redaction behavior, that errors come back with offending resources, and crucially that the draft is consumed on success — matching and enriching destructiveHint=true and idempotentHint=false. It also states what does not happen (nothing deploys).

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 action, then branches on draft type before covering validation and side effects. Dense but every clause carries information; slightly long as a single block, though nothing is wasteful.

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?

With no output schema, the description supplies the missing behavioral picture: validation criteria, return-on-error semantics, secret redaction, draft consumption, and the fact that no deployment occurs. An agent has what it needs to invoke and interpret the result.

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 100% with all three parameters documented in the schema, so the baseline is 3. The description implies the draft context but adds no syntax or format detail for channel, draft_id, or changelog beyond what the schema already provides.

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 and resource (publish a stack profile builder draft) and distinguishes the two branches: a new-profile draft creates the profile at version 1, while an existing-profile draft adds the next version. This separates it cleanly from create_stack_profile_draft, save_stack_profile_version, and get_stack_profile_draft.

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?

Explains the context that selects this tool (a draft exists and is ready to become a profile version) and routes the agent to the draft edit tools when validation fails. The 'nothing deploys' note implicitly scopes it away from deploy/apply tools, though no sibling is named explicitly as the alternative.

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