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

Annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint) already indicate safe, non-destructive behavior. The description adds valuable behavioral details: returns most recent events, mark_read flagging behavior, polling support, and the nature of returned data (source, citation_uri, raw payload). No contradictions.

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 core action, and every sentence adds value. It efficiently covers purpose, key features, and an alternative access method without unnecessary detail.

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?

Despite having no output schema, the description explains return fields (source, citation_uri, raw event payload) and mentions the limit parameter's range (1-200). Given the tool's simplicity and the rich annotations, the description provides complete contextual information for effective use.

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 input schema (100% coverage). The description adds functional context (e.g., 'Filter by type and/or since', 'Set mark_read:true to flag returned events read', 'Polls work fine') that aids understanding beyond the schema fields.

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 what data is returned (source, citation_uri, raw event payload) and provides filtering options. This distinguishes it from related tools like list_subscriptions or subscribe.

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 explains when to use the tool and provides context: filtering by type and since, setting mark_read, and polling suitability. It also mentions an alternative HTTP endpoint for scripts/dashboards. However, it does not explicitly contrast with sibling tools or state when not to use.

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