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

Annotations only cover safety/idempotency, and the description adds substantial context beyond them: the REPLACE-not-merge hazard with silent key loss, required-prerequisite reads, and FORBIDDEN failure modes for non-Growth callers. The silent data loss on partial actionConfig sits slightly in tension with destructiveHint=false, though a full-object PATCH is itself non-destructive, so this is disclosure rather than contradiction; what's missing is behavior on unknown automationId or what the response confirms.

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 operation and the highest-risk caveat, and every sentence carries actionable content. The one wasteful element is the enumeration of all nine updatable field names, which largely restates the input schema's property list.

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 an 11-parameter, nested-object mutation tool with no output schema and no annotations about returns, the description covers the prerequisites, the failure modes, the merge pitfall, and points to a docs resource for meta_capi authoring. What it leaves unstated is what a successful response contains and how 'conditions' arrays interact with triggerType, both of which an agent may need.

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% across 11 parameters, so the description carries the burden and does so for the riskiest ones: actionConfig replace-vs-merge semantics, segmentId/branchId capability requirements, and enabled as the only universally permitted meta_capi edit. It adds little for name, triggerType, conditions, delayMinutes, and the enum values, which the agent must infer from the schema alone.

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 and resource ("PATCH an existing automation rule on a tenant-owned webinar") and specifies partial-update semantics ("send any subset... at least one field is required"). That phrasing separates it cleanly from automations_get, automations_delete, and automations_find_matching without needing to name them.

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?

It gives an explicit conditional workflow: to change one actionConfig field, call automations_get first, merge, then send the full object. It also states plan-gating conditions (segmentId/branchId need webinars.adaptive/Growth; meta_capi edits need Growth, but enabled:false always works), which tells the agent when this call will and won't succeed.

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