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

Annotations declare readOnlyHint, openWorldHint, idempotentHint true, destructiveHint false. Description adds behavioral context: returns most recent, carries source/citation_uri/payload, mark_read behavior flags events read so next call shows only newer, and polling works fine. 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?

Single paragraph, front-loaded with main purpose, then details on return content, filtering, mark_read, and alternative access. Every sentence is informative with no redundancy. Efficient and well-structured.

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?

No output schema, but description explains return values (source, citation_uri, raw payload). Covers all 5 parameters, behaviors, and alternative access. Complete for a retrieval tool with good annotations. No missing context for agent invocation.

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?

Schema coverage 100%. Description adds beyond schema: clarifies type filters to one subscription type, limit range (1-200, default 50), since as ISO timestamp for fired_at>=, mark_read flags read, unread_only returns only where read_at null. Provides constraints and defaults.

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?

Clear verb ('Pull') and resource ('fired events from your subscription feed'). Distinguishes from siblings like fetch_feed and read_feed by specifying it returns the most recent alerts with source, citation_uri, and raw payload. Explicit about filtering capabilities.

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?

Provides practical usage guidance: filter by type and since, set mark_read to affect future calls, defaults (limit 50), and polling-friendly. Also mentions alternative access via GET URL for scripts/dashboards. Gives context for effective use without explicit sibling exclusions but still strong.

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