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

The description discloses the mark_read side effect (flags returned events read, so next call only shows newer ones), which goes beyond the readOnlyHint annotation. It also reveals return payload composition (source, citation_uri, raw event payload) and the alternative HTTP endpoint, adding substantial value beyond structured 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?

Four sentences packed with relevant information. Front-loaded with 'Pull fired events from your subscription feed', then immediately covers return format, filtering, mark_read side effect, and alternative access. No wasted words.

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 fairly simple polling tool with 5 params and no output schema, the description explains the return format, filtering, and stateful behavior. It doesn't explicitly mention limit or unread_only, but those are documented via the schema, so completeness is high given richness.

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% and the description adds semantic examples (type like sec_8k, since as ISO timestamp) and explains mark_read behavior. Limit and unread_only are covered by the schema, so the description compensates well where needed.

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?

Description clearly states the tool pulls fired events from the subscription feed, which is a specific verb+resource. It distinguishes from siblings like list_subscriptions, subscribe, and unsubscribe by focusing on retrieving alerts already written to the feed.

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 clear context: says polling works fine, mentions filtering by type and since, and describes mark_read behavior. It does not explicitly name sibling alternatives or when-to-use vs not, but the usage context is strong enough for an agent to decide when to invoke.

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