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

Annotations already declare destructiveHint=true, readOnlyHint=false, and openWorldHint=true, but the description adds significant behavioral context: changes are proposals applied only after human approval or auto-policy, and creations are paused with no spend. It also points to get_tool_schema for operation parameters, though it omits auth requirements and rate limits.

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 description is a single, front-loaded paragraph that lists operations, then explains proposal/creation behavior, then points to get_tool_schema. Every sentence contributes necessary information, though the operation list is long and could be slightly better structured.

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?

Given 14 operations, no output schema, and 0% schema description coverage, the description adequately covers the overall proposal/approval model and the paused-creation behavior, and it directs the agent to get_tool_schema for per-operation parameters. It does not describe return values or how to check proposal status, but those gaps are minor for a dispatcher tool.

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 0%, and the description only says 'Parameters of an operation: get_tool_schema.' It lists the operation enum values (already in the schema) but gives no meaning for the nested params object. Delegating to another tool is helpful but does not compensate for the lack of parameter semantics in the description itself.

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 states 'TikTok Ads, change operations' and enumerates all supported operations, giving a specific verb (change) and resource (TikTok Ads) with clear scope. It distinguishes itself from the read-only tiktok_ads sibling by naming the platform and listing mutation operations, although it does not explicitly reference alternatives like tiktok_ads or propose_change.

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 description provides critical context that changes to existing objects are proposals requiring approval or auto-policy, and that new objects are created paused. However, it does not explicitly state when to use this tool vs. sibling alternatives such as propose_change, approve_change, or get_change_status; usage is implied by the platform and operation list.

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