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

The description states that setting mark_read:true will 'flag returned events read so the next call only shows newer ones,' indicating a state mutation. The annotations declare readOnlyHint=true, which implies no state change. This is a direct contradiction, and the description fails to reconcile this side effect with the read-only annotation.

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 description is concise and well-structured: it opens with the core purpose, then covers the returned data fields, filtering options, the mark_read behavior, and a useful alternative access method. Every sentence contributes unique information without redundancy.

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?

With no output schema, the description explains key returned fields and the effect of mark_read. It omits the full response shape and how unread_only interacts, but the tool's simplicity and the schema's parameter descriptions make this acceptable. The polling guidance adds practical completeness.

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?

All 5 parameters are fully described in the schema, giving a solid baseline. The description adds meaningful context by providing a concrete type example ('sec_8k'), clarifying the ISO timestamp format for since, and explaining the functional effect of mark_read beyond the schema's property 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 begins with 'Pull fired events from your subscription feed,' making the primary verb and resource explicit. It further clarifies the content of the alerts (source, citation_uri, raw event payload), which distinguishes it from sibling tools like list_subscriptions and recent_changes.

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 provides concrete usage context: it mentions filtering by type and since, supports polling ('Polls work fine'), and offers an alternative external endpoint for scripts/dashboards. It does not explicitly compare against sibling tools, but the guidance is clear enough for most scenarios.

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