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

Annotations already cover readOnly/non-destructive/non-openWorld, and the description adds a lot beyond them: data is cached, membership-based filtering excludes accounts TikTok refuses, cursors can be rejected/expired, and 'complete' describes pagination rather than upstream sync coverage or create permission. That last clarification is exactly the kind of trait annotations cannot express.

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 long but front-loaded and nearly every sentence carries information about behavior, pagination, or constraints. Minor slack exists (the Meta-MCP mirroring aside and the explicit REQUIRED/EXAMPLE boilerplate), but nothing is truly redundant.

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 4-param read tool with no output schema, the description supplies the row shape (owner_bc_name), page semantics, and cursor lifecycle that an output schema would otherwise provide. The only omission is connection_context, which does not block correct invocation for the common path.

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%, so the description must carry the load, and it does for three of four params: limit (default 20, max 50), search (case-insensitive native id/name lookup), and cursor (sourced from previous response, stale cursors require a restart). The fourth parameter, connection_context, is never mentioned, leaving a gap that keeps this below 5.

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 opening sentence states a specific verb+resource+scope: list cached TikTok ad accounts (advertisers) for the authenticated tenant. It distinguishes itself from siblings like assets_list_business_centers, assets_list_tt_accounts, and assets_list_apps, and even clarifies the addressee semantics ('advertisers'). An agent can pick this tool without opening the schema.

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?

It gives real usage context: only advertisers the connected member can currently operate are listed, and that the result mirrors the Meta MCP equivalent. It also prescribes how to iterate (keep the same tool/filters/limit, follow next_cursor serially) and when to restart page one. It stops short of naming an explicit alternative sibling or stating when NOT to use it, so not a 5.

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