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

Annotations (readOnlyHint, idempotentHint, destructiveHint) already indicate safe read behavior. The description adds key behavioral details: mark_read true flags events as read affecting future calls, and each event carries source, citation_uri, and raw payload. No contradiction 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 sentences, front-loaded with the primary purpose, then detailing parameters, side effects, and an alternative access method. Every sentence adds value with no redundancy.

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 the tool is read-only, idempotent, has full schema coverage, and annotations covering safety, the description is complete. It explains filtering, side effects, and alternative access, leaving no significant gaps for an AI agent to select and use the tool correctly.

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 covers all 5 parameters with descriptions (100% coverage). The description enhances understanding by providing examples ('e.g. sec_8k') and clarifying the effect of mark_read. This adds meaningful context beyond the schema's 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 it pulls fired events from a subscription feed, specifying the resource ('subscription feed') and action ('pull fired events'). It also mentions filtering by type and since, but does not explicitly differentiate from sibling tools like list_subscriptions or search_articles, though contextually distinct.

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 mentions an alternative HTTP endpoint for scripts and dashboards, implying usage for polling. However, it lacks explicit guidance on when to use this tool versus alternatives (e.g., when to use search_articles instead), nor does it state prerequisites or exclusions.

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