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

The description discloses important behaviors beyond annotations: it returns raw event payloads with source and citation_uri, supports filtering by type and since, and the mark_read flag changes future outputs. It also states that polling is safe, which complements the readOnly/idempotent hints. No contradictions with annotations.

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 three sentences, front-loaded with the primary purpose, and each sentence adds value: what it returns, how to filter, and the alternative access method. No redundant or filler content.

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 tool with five optional parameters and no output schema, the description covers the return format, filtering, the mark_read side effect, and even provides an external endpoint for programmatic access. It is self-sufficient for understanding the tool's behavior, with schema covering parameter details.

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?

While the schema already provides descriptions for all five parameters, the description adds meaningful context such as an example type ('sec_8k'), the consequence of mark_read (next call shows only newer events), and clarifies the semantics of 'since' as an ISO timestamp. This goes beyond the schema's standalone parameter descriptions.

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 opens with a clear, specific action: 'Pull fired events from your subscription feed.' It identifies the resource (subscription feed) and distinguishes the tool from siblings like list_subscriptions, which manages subscription settings rather than returning event data.

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 practical usage context: polling is supported, and the same feed is available via HTTP for scripts/dashboards, implying the tool is optimized for interactive use. It also explains the effect of mark_read on future calls, guiding when to set it. However, it does not explicitly contrast with sibling tools like search_items or recent_changes, leaving some ambiguity about when to prefer this over alternatives.

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