whats_new

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

With no annotations, the description carries the full behavioral burden and does so well. It discloses the persistent cursor file location, the default mark_seen side effect that advances the cursor, and the grouping/ordering semantics. This gives an agent a realistic model of stateful behavior.

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?

The main purpose is front-loaded in a single precise sentence, followed by compact cursor mechanics. There is no filler, repetition of schema fields, or unnecessary detail.

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 stateful tool, the description covers the full lifecycle: first call, cursor location, default advancement behavior, grouping, and ordering. Since an output schema exists, omitting return-value details is acceptable.

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?

The schema only provides the parameter name, type, and default; the description explains that mark_seen controls whether the cursor advances and how that affects future calls. The false branch is not explicitly spelled out, but it is easily inferred from the described behavior.

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 first sentence states a precise operation: return every message across all chats since the cursor, grouped by chat with oldest first. This clearly distinguishes it from siblings like read_thread (single chat) and search, while the cursor mechanism separates it from list_chats.

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?

The description gives clear context about first-call behavior and cursor advancement, but it never explicitly says when to prefer whats_new over read_thread, search, or list_chats. The polling use case is implied rather than stated with alternatives or exclusions.

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