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

The description states that setting mark_read:true flags returned events as read, which implies a modification of state. However, annotations declare readOnlyHint:true, indicating no state change. This is a direct contradiction. Additionally, the mark_read feature undermines idempotentHint:true since repeated calls with the same parameters can yield different results. The description fails to align 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?

The description is four sentences, front-loaded with the core purpose, followed by payload details, filtering, mark_read behavior, and polling suitability. Every sentence serves a clear purpose, and there is no redundancy or fluff. It is appropriately concise and well-structured.

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 rich schema (100% coverage) and annotations, the description covers the return format (source, citation_uri, payload), filtering options, mark_read behavior, and polling. It also provides an alternative access method. However, it does not explain default limit or behavior when both mark_read and unread_only are set, but these are minor omissions for a read tool with good schema documentation.

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%, so each parameter has a baseline description. The tool description adds value by providing examples (e.g., 'sec_8k' for type), explaining that 'since' refers to fired_at >= time, and clarifying the effect of mark_read on subsequent calls. This contextual information enhances understanding beyond the schema.

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 and returns recent alerts. It specifies what each alert carries (source, citation_uri, payload) and mentions filtering by type and since. While it does not explicitly distinguish from siblings like fetch_feed, the purpose is specific and unambiguous.

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 mentions polling is fine and provides an alternative URL for scripts/dashboards, giving some usage context. However, it does not explicitly state when to use this tool versus alternatives (e.g., fetch_feed, read_feed) or when not to use it (e.g., for historical data not in feed). The guidance is implicit rather than explicit.

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