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

Goes well beyond the annotations: it discloses the credit spend, the side effect of saving onto the item and replacing any earlier AI draft (consistent with destructiveHint=true), that the save is best-effort ('attempts'), and the retry contract keyed on idempotency_key. The keyed-retry statement is explicitly conditional and does not contradict idempotentHint=false, which describes unkeyed natural idempotency.

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?

Four short sentences, front-loaded with what the tool does, followed by side effects, cost, the sibling contrast, and the retry contract. No filler and nothing buried.

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 credit-spending, destructive, non-readOnly tool with no output schema, the description covers the essential uncertainty: cost, side effect, non-sending semantics, and retry behavior, and it notes the return value (suggested reply text). The remaining gap is that several optional parameters, notably workspace_id, are unexplained despite this being a content-creating 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 description coverage is only 50%, and the description only adds meaning for two of six parameters: `id` (the target inbox item) and `idempotency_key` (repeat calls return the original result). brand_id, workspace_id, body, and query receive no explanation, leaving real gaps the schema does not fill.

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 ('Generate an AI reply draft for an inbox item by id') and immediately scopes it against the sibling that actually sends a reply. An agent can distinguish it from aidelly_reply_to_inbox_item without inspecting either schema.

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?

Gives explicit when-to-use (drafting a reply for an inbox item) and when-not ('Sends nothing; aidelly_reply_to_inbox_item sends a reply'), naming the alternative and the distinguishing condition. It also flags cost ('Spends AI credits'), which is decision-relevant before invocation.

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