create_model_choices

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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that: writes default to a dry-run preview, the tool verifies persisted labels and allocated values after execution, and publication is a separate step. The dry-run default meaningfully tempers the destructive hint.

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 tight sentences, front-loaded with the core action and prerequisites, with constraints following. A few telegraphic fragments ('Default preview.') are efficient rather than wasteful, though slight expansion would aid readability.

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 10-parameter mutation tool with no output schema, the description covers the preview/write split and post-write verification reasonably well. It does not clarify the alias parameter duplication (which makes 'required parameters: 0' confusing) or what the preview response contains, leaving gaps an agent must resolve by reading the schema.

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 only 40%, so the description has to compensate, and it partly does: it explains omitting 'value' to get native publisher-based allocation and that supplied values/labels must be unique. However it says nothing about the schema_name vs schemaName alias pairs, the label/description language-code structure, or the display_name shape, leaving the camel/snake duplication unexplained.

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 ('Create a global Picklist choice') plus prerequisites (existing unmanaged solution, publisher prefix), which distinguishes it from siblings like create_model_column, change_model_choice_value and publish_model_choices. It does not name an alternative explicitly, but the 'global' scope and 'no automatic publication' clause implicitly separate it from publish/update tools.

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?

Guidance is present but mostly parameter-level: default preview behavior, when to omit an option value, and the note that publication does not happen automatically (implying a separate publish call). There is no explicit statement of when to choose this over get_model_choices or create_model_column, so usage must be inferred.

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