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

Annotations already declare read-only, idempotent, open-world. Description adds behavioral details: return format (source, citation_uri, payload), mark_read side effect (flags events read), and that polls work fine. No contradiction.

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?

Concise four sentences, each adding distinct value: core action, return contents, filtering options, mark_read effect, and alternative access method. Front-loaded with main purpose.

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 no output schema, description covers return structure and parameter behaviors adequately. Annotations handle safety. Context about feed persistence and alternative access is useful. Feels complete.

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 is 100%, baseline 3. Description adds meaning by explaining the purpose of type, since, mark_read, and implying unread_only usage. Adds value over bare schema.

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?

Clearly states it pulls fired events from subscription feed, with specific resources and capabilities. Distinguishes from siblings like subscribe/unsubscribe by focusing on retrieval.

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 context on filtering by type and timestamp, mark_read behavior, and polling suitability. Mentions alternative HTTP endpoint. Lacks explicit when-not-to-use but still strong.

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