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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the mutation profile is covered. The description adds genuinely useful context beyond that: the write is a PARTIAL SAVE affecting ONLY 'Attribution' while all other v1/v2 fields stay untouched — valuable for a tool flagged destructive. It stops short of auth/permission requirements or rate-limit behavior.

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 critical constraint (PARTIAL SAVE / scoped to one field) is front-loaded, and each sentence carries substantive meaning. It is dense and somewhat long, with the trailing multi-touch/referral background being nice-to-have rather than strictly necessary, but nothing is redundant filler.

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 mutation tool with no output schema, the description plus annotations plus 100%-covered nested schema cover the essentials, including the crucial destructive-scope clarification. The only real gap is that it doesn't address authorization or what a successful save returns, though with no output schema that is a minor omission.

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%, so the schema already documents title_id and every nested AttributionDefinitions field in rich detail. The description adds conceptual framing of the touch chain (first touch immutable, last touch tracks win-backs) but no parameter-level syntax beyond what the schema supplies. Baseline 3 is correct when the schema does the heavy lifting.

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+resource (writes the 'Attribution' field of TitlePublicConfigurationModel) and immediately scopes it as a PARTIAL SAVE, which is the exact detail that differentiates it from the many other save_* siblings. The follow-on 'Acquisition attribution — how the engine records WHERE a player came from' nails down the domain. An agent can tell what this does 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?

Usage is implied by 'This section only tunes that recording', describing what to configure when tuning acquisition behavior. However, it never states when to reach for this tool versus get_attribution (read), or any precondition such as requiring an existing title. No explicit alternatives or exclusions are given, so it lands at implied-usage level.

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