List the connected account’s TikTok posts

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

Annotations already include readOnlyHint=true and destructiveHint=false, but the description goes beyond by explaining the unresolved field semantics (id not returned means not on account or deleted, never zero), and crucially discloses that the TikTok API offers no way to edit or delete published posts—critical behavioral context for agents. It also notes 'Read-only, 0 credits' and requirements like 'Needs TikTok connected.' No contradiction with annotations.

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 longer than average but well-structured: it opens with the core purpose, lists the two modes, then explains the unresolved behavior and the edit/delete limitation. The warning about no-edit capability is a bit verbose but earns its place because it prevents futile search for a tool. The use of bullets and bold headings improves scannability, though some trimming could make it leaner without losing value.

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 list operation with only two optional parameters and no output schema, the description covers all necessary aspects: the data returned, the two invocation patterns, the unresolved field semantics, the account restriction, the read-only nature, and the platform limitation on edits. An agent has everything needed to call this tool correctly and to set user expectations about capabilities.

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?

The schema already has 100% coverage with descriptions for both limit and videoIds. The description adds value by explaining the interaction: limit is ignored when videoIds is given, and videoIds reads specific posts regardless of age. It also clarifies the meaning of unresolved ids. While the baseline is 3 with high schema coverage, the description meaningfully enhances the semantics beyond the 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?

The description explicitly states 'The connected account’s own TikTok posts with per-video stats' and names the exact stats (views, likes, comments, shares, duration, cover image, link). It also distinguishes between the two invocation modes: listing recent posts with no arguments and reading specific posts via videoIds. This clearly separates it from sibling tools like list_tiktok_comments or search tools, leaving no ambiguity about what it does.

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?

The description provides explicit guidance on when to use each mode: with no arguments for the most recent posts, with videoIds to answer 'how did that specific video do' without paging. It also states 'Only ever the connected user’s OWN videos,' which prevents misuse. While it doesn't name alternatives like list_tiktok_comments, the two-mode usage is clearly defined, and the warning to not look for a tool to edit/delete posts implicitly steers toward this tool's appropriate use.

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