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

Annotations already declare readOnly/non-destructive/closed-world, and the description adds real behavioral context: the snapshot is sanitized and taken from the task's original payload/result, while include_live triggers additional reads against /campaign/get, /adgroup/get and /ad/get. It also warns that comparison is the agent's responsibility. It could still note auth or failure behavior, but this is well beyond the annotation baseline.

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-loaded with the purpose, then return semantics, then required/optional params, then an example call. Dense and mostly waste-free, though the EXAMPLE line largely restates information already implied by the schema and REQUIRED/Optional line.

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?

No output schema exists, so the description usefully characterizes the returned creation_snapshot and live_snapshot and the intended comparison workflow. Missing details are minor: connection_context is untouched and no mention of error or empty-result behavior.

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 0%, so the description carries the load and does so for the two meaningful parameters: task_id is marked REQUIRED and include_live is described as optional with default false and with the concrete downstream effect of fetching live config. connection_context is left unexplained, which is the only real gap.

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+resource ('Return a sanitized TikTok creation snapshot for one create task') and explains what the snapshot contains and its origin. It implicitly distinguishes itself from read-only siblings like tasks_get_status or overview_get_live_configs, but never names an alternative tool outright.

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?

Clearly tells the agent when to set include_live=true (to also fetch current TikTok config and detect later manual Ads Manager edits) and assigns the comparison work to the agent. No explicit when-not or named alternative among the many sibling task tools, so it stops short of a 5.

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