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

Annotations only declare readOnlyHint=false, destructiveHint=true and openWorldHint=false; the description adds genuinely non-derivable context: that the write is a partial save leaving all other fields untouched, that clients can never write this store, and that Runtime-scope state is written only by CloudCode. It still does not say whether the field is replaced wholesale or merged, which matters for a destructive save.

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 partial-save constraint is correctly front-loaded, but the Scope/Bucket semantics are explained in the description and then again in the schema and enum descriptions, so the text is longer than it needs to be for its information content.

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 nested 2-parameter mutation with no output schema, the description covers the critical unknowns: partial-save scope, that values are stored elsewhere, and the scope/bucket write restrictions. It omits the read counterpart (get_title_custom_data) and any mention of required permissions or whether the saved field is replaced atomically.

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 both parameters and the nested TitleCustomDataDefinitions properties are already fully documented with recommended values and limits. The description restates the Scope/Bucket meaning that the schema already carries in enum descriptions, adding conceptual framing rather than new parameter-level guidance.

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 opens with a specific, distinguishing statement: 'PARTIAL SAVE: writes ONLY the TitleCustomData field of TitlePublicConfigurationModel; all other v1/v2 fields stay untouched,' and clarifies it governs the key schema and limits rather than values. That cleanly separates it from save_title_data. The wording drifts into field-level documentation ('SCHEMA + limits for the title-wide key-value store'), which slightly blurs whether the tool saves a schema or a config section.

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?

It explicitly routes value management to alternatives ('the VALUES live in the TitleCustomData store... managed with the dedicated title-data tools (get_title_data / save_title_data)'), which tells the agent when this tool is the wrong choice. It does not, however, mention the sibling get_title_custom_data as the read counterpart, and gives no prerequisites for calling it.

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