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

Beyond annotations (readOnly, idempotent, not destructive), the description reveals that mark_read:true modifies read state so future calls exclude returned events, and that response includes specific fields. This adds valuable behavioral context not captured by annotations alone.

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 concise (3 sentences), front-loaded with the primary action, and each sentence adds distinct value. No redundant or wasteful content.

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 has 5 optional parameters, no output schema, and rich annotations, the description covers the core functionality, return fields, filtering, state mutation, and an alternative access method. It omits details on unread_only and error cases, but these are minor for a read-oriented tool.

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% with good descriptions for each parameter. The description reinforces the meaning of type, since, and mark_read, but does not add significant new semantics beyond what the schema already provides. Baseline of 3 is appropriate.

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 that the tool pulls fired events from a subscription feed, returning most recent alerts with source, citation_uri, and raw event payload. This is a specific verb+resource action, and it distinguishes from siblings like list_subscriptions by focusing on alerts rather than subscriptions.

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 provides usage tips like filtering by type and since, using mark_read for state management, and mentions that polling works and the same feed is available via a GET endpoint. However, it does not explicitly compare to sibling tools or state when to use this tool versus alternatives, so guidance on selection is limited.

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