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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so the safety profile is clear. The description adds valuable behavioral context beyond annotations, such as the effect of mark_read on subsequent calls (only newer events shown) and the fact that the feed is also available via an HTTP endpoint for external use. This enriches the agent's understanding without contradicting the 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 five sentences, each earning its place: purpose, return contents, filtering, mark_read behavior, and polling/alternative access. The key action is front-loaded in the first sentence. There is no redundant language or fluff, making it highly efficient.

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?

With no output schema, the description compensates by specifying that each alert carries source, citation_uri, and the raw event payload. It also covers filtering and mark_read semantics, which are critical for use. It does not explicitly mention the unread_only parameter, but the schema covers that, so it's not a gap. The description is complete enough for an agent to use the tool effectively.

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 is documented in the schema. The description adds extra meaning by explaining the interaction between mark_read and future calls, which is not obvious from the schema alone. It also gives a concrete example for the type parameter ('sec_8k'). This goes beyond the schema's baseline value.

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 opens with a specific verb and resource: 'Pull fired events from your subscription feed.' It further clarifies the exact nature of the tool by explaining it returns the most recent alerts written by the evaluator, which distinguishes it from generic feed readers like fetch_feed or read_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?

The description provides clear context for use: filtering by type and since, marking events read, and polling. It explicitly states 'Polls work fine,' giving a direct usage recommendation. However, it does not explicitly mention when to use this tool over sibling tools like fetch_feed or read_feed, so it stops short of full exclusionary guidance.

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