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

The description directly contradicts the annotation readOnlyHint: true. It states that setting mark_read:true 'flag[s] returned events read so the next call only shows newer ones,' which is a state-changing operation. Despite the description being transparent about this side effect, the annotation falsely claims the tool is read-only. This is a serious inconsistency that could mislead an agent relying on 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 compact, consisting of three sentences that efficiently cover the core action, return fields, filtering, and the mark_read side effect. It front-loads the main purpose and avoids irrelevant details. The structure is logical, though slightly dense; a bullet list could improve scannability, but it remains concise and readable.

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 no output schema and multiple optional parameters, the description is quite complete: it explains return fields (source, citation_uri, raw payload), provides usage patterns, and mentions an alternative access method. It doesn't cover error cases or explicitly state default behavior for mark_read false, but given the annotations (except the contradiction) and simple nature, it's nearly sufficient. The contradiction with readOnlyHint partially undermines completeness, but the description itself is informative.

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?

Although the schema already documents all five parameters with descriptions, the tool description adds valuable semantics beyond the schema: it explains the effect of mark_read on future calls ('next call only shows newer ones'), provides an example value for type ('sec_8k'), and clarifies the 'since' parameter as an ISO timestamp. This enriches the param information beyond the bare schema 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 clearly states the tool's purpose: 'Pull fired events from your subscription feed.' It specifies the resource (subscription feed) and the action (pull/retrieve), and distinguishes itself from sibling tools like recent_changes and recent_cves by focusing on alerts/events. The mention of 'fired events' and 'alerts' makes the tool's scope unambiguous.

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 practical usage context: it mentions polling is fine, explains filtering by type and since, and suggests an alternative access method for scripts/dashboards via a URL. While it doesn't explicitly say when not to use it or compare with specific sibling tools, it gives enough context for the agent to decide when this tool is appropriate, especially with the note about an alternative HTTP endpoint.

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