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

Adds substantial context beyond the annotations: reading never marks anything read, customer details are gated behind an off-by-default dashboard setting that cannot be changed from chat, and when off the answer returns counts and masked addresses. It also documents the prompt-injection defense (customer_text wrapped with trust=untrusted, suspicious flags) and the audit trail, which no annotation conveys.

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 core purpose and dense with useful detail, but the middle is a single run-on sentence crammed with em-dashes and parentheticals, which makes it harder to parse than it needs to be. Every clause carries information, so little is wasted despite the length.

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?

No output schema exists, so the description carries the full burden of describing return shape — and it does: conversation fields, thread mode limits, masking behavior, trust wrappers, and structuredContent.customerText. An agent has everything needed to call and interpret this tool.

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 33% (limit is documented in the schema; threadId and unansweredOnly are not). The description compensates well: it fully explains threadId behavior (whole conversation, oldest first, last 50 messages, 8,000 chars each) and 'unanswered first' implicitly covers unansweredOnly, but it never names limit or unansweredOnly explicitly, leaving a small gap.

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 (Reads) and resource (the app's support Inbox) and immediately scopes the result set: conversations, unanswered first, with the fields returned (who wrote, subject, when, whether the founder owes a reply). The threadId mode is also described, so an agent knows both behaviors without opening the 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?

Explains the two invocation modes clearly (list mode vs. threadId mode) and tells the agent what this is for ('what a founder may call their messages or support emails'). It does not name an alternative sibling (e.g., inbox_reply for responding, live_emails for other email) or state when not to use it, so it stops short of a 5.

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