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

With annotations present, the description still adds meaningful context beyond them: rules are enabled by default, enabled=false saves an inactive rule, the default 'contains' match, and retry-safety via idempotency_key. Auth/permission and rate-limit behavior are not mentioned. The retry-safe claim sits in mild tension with idempotentHint=false, though it clarifies the key-based dedupe mechanism rather than misleading the agent.

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-loads purpose, then required params, then runtime behavior and return/retry semantics. Every sentence does work, though 'Returns the created rule' is largely implied for a create tool and the paragraph is dense.

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 15-parameter tool with nested objects and no output schema, the description usefully states the return value and idempotency contract. But it omits semantics for most non-required parameters (guardrails, responseMode, triggerEvent, campaignDurationDays) that the sparse schema does not fill in, leaving an agent under-informed for a non-trivial configuration call.

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 low (40%) across 15 parameters, so the description would need to compensate. It adds real semantics for three of them (platformAccountId source, keyword required for comment triggers, enabled default) but leaves guardrails, responseMode, triggerEvent, matchType, campaignDurationDays, brand_id, platform, and workspace_id undocumented, so coverage remains partial.

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 ('Create an automatic reply rule') and scopes it to connected Instagram accounts or Facebook Pages. It clearly distinguishes the artifact (an inbox auto-reply rule) but never names a sibling such as aidelly_update_inbox_automation or aidelly_create_content_automation, so differentiation leans on the name.

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 conveys enabling conditions (requires platformAccountId and message; keyword for comment triggers) and default behavior, which implies when to use it. However, it gives no explicit when-to-use vs alternatives or when-not guidance (e.g., update vs create, template vs ai reply).

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