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

With no annotations, the description carries the full behavioral burden. It discloses cursor semantics (since=<next_cursor>, changes cursor in ms) and default behavior for notifications, which is useful, but it never states permissions/auth needs, pagination limits, or result shape.

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?

Dense but compact: purpose is front-loaded, then kind variants, then a concrete example. The terse colon-list style is information-efficient, though the single run-on sentence reduces 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?

For an 8-param tool with no output schema and no annotations, the description should do more: return shape is only implied by the next_cursor reference, and limit plus the session/agent_answer auth flow are not contextualized. Adequate but with clear gaps.

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 25%, so the description must compensate, and it does for several params: it enumerates the kind values, explains since as a cursor, and notes changes takes optional kinds/topic. It leaves limit, session, and agent_answer unexplained (the latter two only via schema), so compensation is 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?

The lead sentence "What is new for you" is abstract, but the following kind breakdown (notifications/dm/changes) pins down the resource being fetched and what each variant returns. An agent can infer this is a poll-for-new-activity tool, though no sibling (read, search, chat) is named to differentiate it.

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 explains what each kind covers and which is the default, which guides param selection, and hints at cursor chaining via since=<next_cursor>. It does not say when to prefer this tool over read, search, or chat, nor any exclusions.

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