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

Annotations already declare a safe read (readOnlyHint=true, destructiveHint=false, openWorldHint=false), and the description adds real context beyond them: the data is cached rather than live, results come back as a 'compact bounded page', a rejected or old cursor forces restarting at page one, and complete means pagination finished rather than upstream sync coverage or permission to create. That last clarification actively prevents a plausible misreading of the return value.

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 resource and the identity-vs-account distinction, then pagination mechanics, then requirements and an example. The pagination guidance is repeated in slightly different words ('follow next_cursor serially' vs 'a rejected or old cursor requires restarting page one'), which is defensible given the failure mode it guards against, but keeps it from being maximally tight.

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?

With no output schema, the description does the work of describing the return shape: a compact bounded page with cursor and complete, plus what complete does and does not mean. Combined with the pagination loop instructions and the explicit 'REQUIRED: none', an agent has enough to invoke and iterate correctly; only connection_context is left unexplained.

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 carries the burden, and it does for three of four parameters: cursor origin (from the previous response), limit (default 20, maximum 50), and search (case-insensitive native id/name lookup). The fourth parameter, connection_context, is never mentioned, leaving one gap that the zero-coverage schema does not fill.

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 and resource ('List cached TikTok accounts') and immediately pins down the scope: data sourced from Business Center assets. It also explicitly disambiguates from the sibling concept of identities ('These tt_account_id values are not posting identity_id values'), so an agent can tell it apart from assets_list_identities without opening either 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?

Gives an explicit when-not and an alternative: for ad creation use assets_list_identities with the exact advertiser_id, then preserve identity_type and identity_authorized_bc_id. It also states the pagination protocol (same tool/filters/limit, follow next_cursor serially until complete=true) and the recovery path for a rejected or stale cursor.

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