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

Adds substantive behavior beyond annotations: approval-gated application, auto-policy limits/reversibility, and paused/no-spend creation. Annotations already cover destructive/read-only/idempotency, and the description does not contradict them. It omits return/status behavior and any auth/rate-limit details.

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?

Front-loads purpose and behavior in a compact set of sentences, with no filler. The long operation enumeration is somewhat redundant with the enum in the schema but still readable and scoped.

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?

Covers the essential proposal/creation workflow and points to get_tool_schema, which is enough to start discovery. However, for a 13-operation mutation dispatcher with no output schema and no per-operation parameter descriptions, it omits return values, follow-up status checks, and explicit routing to approve/status tools.

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?

The only parameter-related guidance is that operation parameters come from get_tool_schema; the actual semantics of params and per-operation requirements are absent. The operation list merely repeats the schema enum, and schema coverage is 0% for the nested params object.

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?

Names the resource and operation family explicitly and enumerates the supported changes, so an agent can see this is the Snapchat Ads mutation entry point. It does not explicitly route reads to snapchat_ads or generic proposals to propose_change, so it falls short of full sibling differentiation.

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?

Explains the key usage condition: existing-object changes are proposals that require approval or auto-policy eligibility, and new objects are created paused. It also directs agents to get_tool_schema for operation parameters. It does not name when to prefer snapchat_ads, approve_change, or get_change_status.

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