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

Annotations only declare it as a mutating, destructive, non-open-world write. The description adds valuable specifics beyond that: it is a partial write that preserves all other configuration fields, and shared SSV/report secrets are never stored here, only the TitleSecrets entry name. It does not discuss response shape or idempotency, keeping it shy of a 5.

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) is front-loaded in the first clause, which is the right structure. The second sentence enumerates the advertising domain at length and largely duplicates the schema's own AdvertisingDefinitions description, but it earns some of its space by surfacing the secrets-exclusion rule.

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 high-complexity, deeply nested mutation tool with 100% schema coverage and no output schema, this description supplies the key non-schema facts an agent needs: partial-write scope and the secrets-vs-secret-name boundary. It omits any mention of the operation's response or failure behavior, but those are minor given the schema richness.

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% and the nested AdvertisingDefinitions schema is itself extremely detailed, so the schema does the heavy lifting. The description reinforces coverage of the value payload (placements, providers, consent, SSV) and clarifies that secrets are referenced by name, but adds little parameter-level meaning the schema doesn't already carry.

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?

Opens with a specific verb+resource and scope: 'PARTIAL SAVE: writes ONLY the Advertising field of TitlePublicConfigurationModel; all other v1/v2 fields stay untouched.' This makes it distinguishable from get_advertising and from the many sibling save_* tools, which each target a different configuration domain.

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 'PARTIAL SAVE' framing implies when this tool is appropriate (targeted advertising edits that must not disturb other fields), which is meaningful usage context. However, it never names the read sibling get_advertising as the prerequisite/recovery path and states no explicit when-not conditions or prerequisites.

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