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

readOnlyHint=true and openWorldHint=true already declare this as a safe, externally-scoped read, so the description's burden is low. It adds what the entries contain (display name and avatar), but says nothing about empty results, whether identities are TikTok-scoped, or ordering/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?

One front-loaded sentence with no filler. It is efficient, though a single flat clause leaves no room for structuring the scope/return distinction.

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?

A read-only list tool with no output schema needs enough to call it correctly: the description lacks any signal about the required adAccountId, how platform/accountId/profileId interact for a 'TikTok' tool whose accountId is described as Facebook, or what the response list looks like.

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?

At 75% schema description coverage the schema carries most of the load, but the required adAccountId has no schema description at all and the description only gestures at it ("on this ad account"). It also does not reconcile the TikTok framing with accountId being documented as a "Facebook accountId".

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 gives a specific verb and resource ("List the brand identities") and clarifies what an identity is ("display name and avatar") plus its scope ("a TikTok ad can run as on this ad account"). That separates it from ads_create_identity, though no sibling is 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?

Usage is implied — you list identities to pick one for a TikTok ad — but the description never states when to call this versus ads_get_account or ads_create_identity, nor any prerequisite such as having a connected TikTok account. The agent must infer the workflow position.

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