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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=true, so safety is fully covered structurally. The description mostly restates this ('read-only', 'changes nothing') and adds only the operation inventory plus the get_tool_schema routing hint, not richer behavioral context like return shape or pagination.

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?

Purpose is front-loaded, followed by the operation inventory and the key read-only constraint. The long operation list is dense but necessary given there is no per-operation schema, and no sentence is filler.

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 13-operation dispatcher with nested objects, no output schema, and 0% parameter coverage, the description is thin: it names operations but explains none of their inputs, outputs, or distinctions. The get_tool_schema pointer is the main completeness feature, but per-operation context is deferred entirely.

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 burden. It partially compensates by telling the agent where to find per-operation parameters (get_tool_schema), but gives no semantics for the enum values or the 'params' object format, leaving the agent dependent on a second call.

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 a specific verb and resource ('TikTok Ads, read-only operations') and enumerates all 13 supported operations. An agent can tell this is the read counterpart to tiktok_ads_changes, though the sibling is never named explicitly.

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?

'Changes nothing in the ad account' implies read-only usage and contrasts implicitly with the write sibling, but there is no explicit when-to-use / when-not guidance or named alternative. The pointer to get_tool_schema hints at a discovery workflow but isn't framed as a usage rule.

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