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

Annotations already declare it as a mutating, open-world, idempotent, non-destructive operation, and the description is consistent with that while adding context the annotations cannot carry: the async return of job_id, the polling lifecycle, the fact that max_credits is a hard ceiling rather than a final charge, and the idempotency_key retry rule. Billing and retry semantics are exactly the behavioral detail an agent needs before committing a paid job.

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?

Four dense sentences with zero filler, front-loaded with the action and its precondition. Each sentence carries a distinct, non-redundant constraint (approval, mutual exclusivity, async polling, ceiling semantics, retry key).

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 paid asynchronous mutation tool with a nested object parameter, the description covers approval requirements, input constraints, return behavior, polling, and retry semantics. An output schema exists, so return values need not be spelled out, and the description still notes the immediate job_id response.

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%, so the baseline is 3, but the description adds real meaning beyond the schema by clarifying that max_credits is a ceiling and not a promised final charge, and by restating the pack_id/new_pack mutual exclusivity as an invocation rule. It does not add syntax or format guidance for max_rounds or intention beyond what the schema already supplies.

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 opening sentence names a specific verb and resource ('Start a ... pack build') and qualifies it as paid and asynchronous, which immediately separates it from the read-only siblings. It also notes exactly what is being created (a new pack or a build of an existing one), so an agent can distinguish it from get_pack_build_status without opening the schema.

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 the precondition for use ('after the user explicitly approves max_credits'), the input constraint ('supply exactly one of pack_id or new_pack'), and routes to the sibling tool with its own condition ('poll get_pack_build_status only while active=true'). This is explicit when-to-use plus a named alternative, which is the top of the scale.

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