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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds valuable behavioral context: the mark_read parameter modifies state by flagging events as read, affecting future calls. It also explains the feed is persisted and accessible elsewhere, which goes beyond 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?

The description is concise with two sentences: the first covers core functionality and return structure, the second details filters and mark_read behavior. It ends with a useful note about alternative access. 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 absence of an output schema, the description adequately explains return fields (source, citation_uri, raw payload) and filtering options. It covers parameters and state behavior. Missing explicit ordering or pagination details, but overall complete for a simple read tool with annotations.

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 all 5 parameters described. The description adds meaning beyond the schema: it specifies ISO timestamp format for 'since', explains the effect of mark_read, and gives an example filter type ('sec_8k'). This compensates for the schema's minimal 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?

The description clearly states the tool pulls fired events from a subscription feed, returning recent alerts with specific fields like source and citation_uri. It distinguishes itself from sibling tools focused on subscriptions (list_subscriptions, subscribe, unsubscribe) by emphasizing real-time alert retrieval.

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 clear context for use: retrieving recent alerts with optional filters for type, time, and read status. It mentions polling works fine and offers an alternative GET endpoint for scripts/dashboards, but does not explicitly exclude other tools or specify when not to use it.

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