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

Annotations already declare readOnlyHint/idempotentHint and the safe read profile, so the bar is lower. The description adds real behavioral context beyond that: output is 'content-light', names only are surfaced and 'never message text', and it prescribes a short two-to-three-line response with one suggested action. It doesn't cover pagination or the since-window edge behavior, but the added disclosure is substantial.

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?

It is front-loaded with the core purpose ('A short, content-light check-in') and every clause carries information. The main body is one very dense, comma-chained sentence that packs seven content categories plus output-style guidance, which costs some readability.

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 structure needn't be explained, and the description covers the deliverable shape (short, one action), the content categories, and the read_conversation boundary. What is missing is the relationship to overlapping siblings like whats_waiting, but for calling the tool correctly it is essentially complete.

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 100% and the single optional 'since' parameter is fully documented in the schema including its 24h default and 14-day cap. The description's 'since a time' phrasing adds nothing beyond that, so the baseline 3 for schema-covered params is correct.

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 names a specific verb and resource ('what's new in the person's Stream since a time') and enumerates the card types it surfaces (new cards, waiting plans, meetups, writers, knocks/drafts, pending suggestions), so an agent knows exactly what it returns. It does not, however, distinguish itself from close siblings such as whats_waiting or list_upcoming, which cover overlapping territory.

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 states the intended context ('Made for a daily check') and gives an explicit exclusion with the alternative named: 'Read messages only if the person asks (read_conversation).' That is a clear when-not rule. It stops short of explaining when to pick this over siblings like whats_waiting, so it is not a full 5.

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