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

Annotations already provide readOnly, openWorld, idempotent, and non-destructive hints. The description adds valuable behavior details: return structure (source, citation_uri, raw payload), mark_read effect on subsequent calls, and the existence of an HTTP endpoint. 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?

Four sentences with no fluff. The first sentence states the core purpose, followed by return structure, filtering options, and mark_read behavior. The final sentence adds practical usage guidance (polling and HTTP endpoint). Every sentence adds distinct value.

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 adequately describes return fields. It covers all major use cases (filtering, mark_read, unread only implied), and provides context for polling and alternative access. Given the tool's complexity and annotations, the description is complete enough.

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%, so baseline is 3. The description adds context by explaining the mark_read flag's behavior (flags returned events as read) and mentions filtering by type and since. It does not mention unread_only, but the schema covers it. The additional context raises the score above baseline.

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 the subscription feed, focusing on recent alerts with specific fields (source, citation_uri, raw payload). It distinguishes itself from sibling tools like list_subscriptions and subscribe by being the tool for retrieving actual alert data.

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 explains mark_read behavior for managing read status across calls. Mentions polling and the alternative HTTP endpoint, giving context on when to use the tool vs. the API. Lacks explicit 'when not to use' guidance for sibling tools but is otherwise clear.

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