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

Goes well beyond the annotations (which only say readOnly=false, destructive=false, idempotent=false) by disclosing that deletion is impossible via the API (OAuthException 200), that event-only rules get an implicit all-pages condition, that casing is normalized, and that custom_event_type is auto-derived. These are exactly the hidden behaviors an agent needs. Minor gap: it does not state auth/permission requirements or whether the call is safe to retry.

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 and dense — the rule-construction logic comes first, then the irreversibility warning. Slightly redundant: the 'leave custom_event_type out and it is derived/set for you' point is made twice in adjacent paragraphs.

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?

An output schema exists, so return values need not be explained, and the description covers everything else an agent needs: valid inputs, auto-applied defaults, preview vs commit, and the irreversibility constraint. Nothing material is missing for correct invocation.

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 carries the full burden, and it does: it documents the full enum of standard pixel events (absent from the schema), the meaning and derivation of custom_event_type, the semantics of url_contains, pixel_id's source, and confirm as preview. Only account_id and name are left without explicit semantics.

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?

Specific verb + resource ('Creates a custom conversion on a pixel') with the object of creation named precisely. It is clearly distinguishable from sibling update_meta_custom_conversion and list_meta_custom_conversions, and the description immediately scopes what a custom conversion consists of (URL rule and/or event rule).

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 states when to pass url_contains, when to pass event, and that both can be combined ('that event fired on that page'). It names the prerequisite source (pixel_id from list_meta_pixels), explains confirm=false as preview, and mandates confirming name/rule with the user before confirm=true.

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