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

Annotations already indicate read-only, idempotent, non-destructive. Description adds valuable context: explains state change with mark_read, polling suitability, and feed persistence. 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?

Three concise, front-loaded sentences. Each sentence adds distinct value: purpose, return fields, filtering, state management, polling advice, and alternative access. No redundancy or fluff.

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?

Describes return fields and filtering, but lacks explicit ordering (though 'most recent' implies recency). No output schema, but description covers key behavioral aspects. Slight gap in pagination or sorting, but adequate for the tool's complexity.

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 covers 100% of parameters with descriptions. Description adds examples (e.g., 'sec_8k' for type, ISO timestamps) and explains the effect of mark_read, going beyond the schema's basic 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?

Clearly states it pulls fired events from the subscription feed, specifies returned fields (source, citation_uri, payload), and distinguishes from sibling tools like list_subscriptions and subscribe. The mention of an alternative endpoint for scripts/dashboards further clarifies its use case.

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 explicit filtering options (type, since) and state management (mark_read). Mentions polling works and gives an alternative REST endpoint, indicating when to use the tool vs. other methods. Lacks explicit when-not-to-use, but the context is clear enough.

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