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

Annotations already indicate readOnly, openWorld, idempotent, and non-destructive behavior. The description adds valuable behavioral details: the 'mark_read' parameter's effect on subsequent calls, the resource format of each alert, and the alternative HTTP endpoint. 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 a single paragraph that is well-structured: it starts with the core purpose, then details return fields and filters, followed by behavior notes and an alternative access method. It is concise without being terse, though slightly verbose in listing alternatives.

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?

Given the parameter count (5) and absence of an output schema, the description covers the essential aspects: what the tool returns (source, citation_uri, payload), how to filter, the 'mark_read' behavior, and polling compatibility. It lacks details on error scenarios or pagination hints, but is sufficient for most use cases.

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?

The input schema has 100% coverage with descriptions. The tool description elaborates on key parameters, like giving an example for 'type' ('sec_8k') and explaining the 'mark_read' side effect. This adds practical meaning beyond the schema's brief 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 uses specific verbs and resources: 'Pull fired events from your subscription feed' and 'Returns the most recent alerts'. It clearly identifies the tool's function and mentions key attributes like source and citation_uri. While it doesn't explicitly distinguish from siblings like 'list_subscriptions' or 'subscribe', the purpose is 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 context on available filters (type, since) and mentions that polls work fine. It also notes an alternative access method via a URL. However, it does not explicitly state when to use this tool vs other query or subscription tools, nor does it give exclusion conditions.

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