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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the bar is lowered. The description still adds meaningful behavioral context: there is no default privacy level, which is a critical fact the agent must surface. It does not describe what happens if no TikTok account is connected, keeping it short of a 5.

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?

Content is front-loaded: the read behavior comes first, then the follow-up instructions. The second sentence is dense and long, packing multiple user prompts together, but every clause earns its place.

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 parameters, no output schema, and full annotation coverage, the description adequately covers what an agent needs to call this and use the result. The only gap is error/edge handling for the no-connected-account case.

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?

Zero parameters, so the baseline is 4. The description goes further by mapping the retrieved settings to the consuming call's parameters (platformTargets.tiktok in create_post), which adds semantic value beyond the empty schema.

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 ('reads') and resource (TikTok account posting capabilities) and enumerates exactly what is returned: account name, privacy levels, comments/Duet/Stitch allowances, and max video length. This clearly distinguishes it from the sibling get_youtube_settings.

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?

Explicitly says when to call it ('before publishing to TikTok'), what to do with the output (show the account name, ask the user to choose privacy, comments, Duet/Stitch, branded content), and where the answers go ('Pass their answers in create_post as platformTargets.tiktok'). No inference required.

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