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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds valuable behavioral details beyond these: it explains that each event carries source and citation_uri, that mark_read:true modifies read state so future calls only show newer events, and that polling is safe. It fully discloses the side-effect of mark_read despite the readOnlyHint, avoiding any 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?

The description is three sentences and front-loaded with the main action ('Pull fired events'). Every sentence adds value: return fields, filtering options, mark_read semantics, and polling/alternative endpoint. There is no verbosity or redundancy, making it easy for an agent to parse quickly.

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?

For a tool with 5 optional parameters, no output schema, and good annotations, the description is quite complete. It explains the return payload (source, citation_uri, raw event), filtering criteria, state-changing option, and even provides a fallback URL. This covers the essential context an agent needs to invoke the tool correctly without needing to infer behavior.

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 has 100% description coverage, so the baseline is 3. The description adds extra meaning by giving a concrete type example ('sec_8k'), specifying the ISO timestamp format for since, and explaining the effect of mark_read on future calls. It does not explicitly cover limit or unread_only, but the schema already describes them well, and the added context for type and mark_read exceeds the 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's function: 'Pull fired events from your subscription feed.' It specifies the resource (alerts in the subscription feed) and the exact output (source, citation_uri, raw event payload). It distinguishes this from sibling tools by focusing on reading alert events, not managing subscriptions or performing other actions.

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 gives clear usage context: filter by type and/or since, use mark_read to advance the feed, and notes that polling works fine. It also mentions an alternative HTTP endpoint for scripts/dashboards, which aids in deciding when to use the tool vs. other access methods. It does not explicitly contrast with sibling tools like recent_changes, but the guidance is sufficient for most use cases.

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