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

Annotations already cover the mutation profile (readOnlyHint=false, destructiveHint=true), and the description adds real behavioral context: local SHA-256 hashing so raw PII never leaves the server, automatic dedup when event_id matches the pixel, and test mode that does not affect real reporting. It omits any note on auth/permission requirements or error handling, which keeps 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?

Front-loaded with the core definition, then dense one-line parameter notes with no filler. The all-caps lead and mixed line formatting are slightly noisy, but no sentence is redundant given the 0% schema coverage.

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 not be described, and the description covers the critical invocation constraints for a 13-parameter mutation tool. Missing: how advertiser_id is obtained (it names list_tiktok_pixels / create_tiktok_pixel for pixel_code but not the account source) and any permissions or rate-limit context.

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 has to carry the load, and it does for the high-risk parameters: identifier requirement (at least one of email/phone/external_id/ttclid), hashing of email/phone, event_id dedup semantics, test_event_code, confirm, and sample event_name values. It leaves url, value, currency, ttclid format and advertiser_id unexplained, so it is strong but not complete.

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 ('sends a server-side conversion event to TikTok (Events API)') and immediately scopes it against the browser pixel, so the agent knows it is the server-side complement to pixel tracking rather than a pixel-config tool. Distinct from send_meta_conversion_event and upload_offline_conversions by channel and API.

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?

Explicit when-to-use cases are given (off-site purchase/lead from CRM, phone, POS; backing up the browser pixel), plus an explicit verify-first workflow via test_event_code and the preview semantics of confirm=false vs confirm=true. Nothing about selection is left to inference.

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