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

The annotations declare readOnlyHint=true and idempotentHint=true, but the description explicitly says 'Set mark_read:true to flag returned events read so the next call only shows newer ones.' This is a persistent state change, directly contradicting the read-only and idempotent annotations. The contradiction warrants a score of 1.

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—three sentences—and front-loaded with the core purpose. It packs return payload details, filtering options, mark_read behavior, and a polling/alternative endpoint without waste. Slightly dense but efficient.

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 compensates by explaining what each alert carries (source, citation_uri, raw payload) and the mark_read lifecycle. It also mentions the HTTP alternative. While it doesn't mention unread_only or limit in prose, those are covered in the schema. Overall, it gives sufficient context for a read tool.

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% parameter coverage with descriptions for all five parameters. The description only adds a few examples (e.g., 'sec_8k' for type, ISO timestamps for since) that are already implied by the schema. It does not add meaningful semantic value beyond what the schema provides.

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 'pulls fired events from your subscription feed' and details what each event carries (source, citation_uri, raw payload). This distinguishes it from siblings like recent_changes and list_subscriptions. The verb 'Pull' and specific resource make the purpose 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 says 'Polls work fine' and provides an HTTP endpoint as an alternative for scripts/dashboards, giving some usage context. However, it does not explicitly state when to use this tool instead of sibling tools, nor does it offer exclusions or when-not scenarios. Usage is implied rather than explicitly guided.

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