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

With no annotations, the description carries the full burden and does disclose the cursor/polling mechanism and a freshness constraint on age_seconds. It says nothing about token expiry, rate limits, error behavior, or what happens if the cursor is stale — significant gaps for a token-gated polling endpoint.

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 short and the continuation rule is present, but the opening is a sentence fragment and the three clauses are loosely strung together, making it cryptic rather than cleanly front-loaded.

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 3-parameter tool with no output schema and no annotations, the description covers the token source, cursor pagination, and a freshness rule, which is a reasonable core. It still omits return shape beyond 'events with ids', 'limit' behavior, and failure modes, so it is adequate but incomplete.

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% (only 'token' is documented), so the description must compensate. It usefully defines 'after' as the returned cursor for continuation, which is genuine added meaning, but 'limit' is left undocumented in both the schema and the description.

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 conveys that this tool yields new trading events carrying ids, tied to a follow token from subscribe_follow, so the resource is identifiable. However, it is written as fragments with no explicit verb ('With a follow token...'), leaving the action ambiguous — it reads partly as a description of the output rather than the operation.

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 gives real procedural guidance: obtain the token from subscribe_follow, pass the returned cursor as 'after' to continue, and act only on events with small age_seconds. It stops short of naming alternatives or stating when this is preferable to siblings like follow_state or get_history, so usage is implied rather than fully routed.

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