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

Annotations already declare readOnly=false, destructive=false, idempotent=false and openWorld=false, so safety is covered. The description adds meaningful context beyond them: per-platform required credential sets and the write-only nature of secrets, which tells an agent credentials cannot be read back. It stops short of noting non-idempotency (duplicate creation) or permission requirements.

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?

All content is on-topic, but the platform and config details are packed into one very long run-on sentence that is hard to scan; a bulleted per-platform list would be both shorter to parse and equally complete.

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 9-parameter, non-idempotent mutation with no output schema and a nested object, the config coverage is strong, but the description omits how name/tags/group_id are used, whether names must be unique, and what identifiers are returned on success.

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 coverage is only 44% and the nested config object is described generically, so the description carries real weight by naming the exact key set each platform expects (e.g. google_ads needs customer_id/conversion_action_id/refresh_token, bigo_events only pixel_id). It still says nothing about name, tags, status, or group_id beyond what the schema shows.

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 opens with a specific verb+resource ('Create a conversion pixel') and immediately enumerates every supported platform, which pins down exactly what the tool produces. It never contrasts itself with update_pixel, get_pixel, or list_pixels, so sibling differentiation is left implicit.

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?

There is no guidance on when to create versus update an existing pixel, no prerequisites, and no mention that platform is required and immutable afterward. The platform/config enumeration is reference material, not when-to-use guidance.

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