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

Annotations already declare readOnly/openWorld=false/destructive=false, but the description adds real provenance context: handles come from cited URLs rather than verified accounts, short links are not resolved, and no scraping or live TikTok requests occur. That last point reinforces the openWorldHint=false in a way an agent can act on.

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 purpose and ordering, then caveats, then the alternative. Every sentence carries information, though the host enumeration (www, m, vm, vt) is dense detail that could be trimmed without much loss.

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 an output schema present, return values need no explanation, and the description covers provenance, ordering, aggregate-vs-pagination behavior, and the drill-down path. Only the filter and pagination inputs are left entirely to the schema, which is a minor gap given the nested filters are self-documented.

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 low at 25%, though the nested filters object is documented in-schema. The description adds one meaningful semantic point — citation shares and totals cover all filtered citations independent of pagination — but says nothing about website_id, page_num/page_size, or the date/model filters. The mention of channel_key refers to a different tool's input, not this tool's parameters.

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 TikTok handles cited in AI answers' — plus the ordering rule (by citations, unattributed URLs last). It also scopes what counts as a handle (profiles, videos, photos across tiktok.com/www/m/vm/vt hosts), which no sibling covers.

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 routes to the alternative: 'Use get_tiktok_pages with channel_key to drill down,' giving both the sibling name and the mechanism. It also implies when-not via the caveat that short links are unresolved and handles are not verified identities.

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