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

The description contradicts the readOnlyHint annotation by disclosing a mutating side effect: setting mark_read:true flags events as read, which changes the feed state for subsequent calls. Since readOnlyHint=true promises no state modification, this is an annotation contradiction, warranting a score of 1.

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 composed of five efficient sentences, each adding distinct value: purpose, return contents, filtering, mark_read effect, and polling/HTTP alternative. It is front-loaded with the core purpose and avoids fluff, making it easy to scan while remaining informative.

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 appropriately explains the return payload (source, citation_uri, raw event payload). It covers key behavioral aspects like filtering and mark_read, and even notes an HTTP endpoint. However, it does not mention unread_only or error conditions, but these are less critical given the schema coverage. Overall, it is sufficiently complete for a read-oriented list 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%, so the baseline is 3. The description adds value beyond the schema by explaining the effect of mark_read (next call only shows newer events) and providing a concrete type example ('sec_8k'). It does not elaborate on limit or unread_only, but the schema already covers them. This extra context justifies a 4.

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 the subscription feed and returns recent alerts written by the evaluator. It specifies the resource (subscription feed), the operation (pull/return), and the returned contents (source, citation_uri, raw payload). This distinguishes it from siblings like list_subscriptions, which likely lists subscriptions rather than alerts.

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 when to use the tool: polling works fine, and it explains filtering by type and since, plus mark_read behavior. It also mentions an HTTP alternative for external scripts, which is a form of alternative guidance. However, it does not explicitly mention when not to use this tool vs. other MCP tools, so it stops short of a 5.

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