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

Annotation Contradiction: the annotations declare readOnlyHint=true, but the description describes a mutating side effect: 'Set mark_read:true to flag returned events read so the next call only shows newer ones.' This directly contradicts the read-only hint. Per rubric, any contradiction yields 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 four sentences, all information-dense and non-redundant. It front-loads the main purpose and then details filters, mark_read, and alternative access. Slightly paragraph-like, but each sentence earns its place; a slightly tighter structure with bullet points could improve scannability.

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?

No output schema exists, but the description covers the key return fields (source, citation_uri, raw payload), filter options, mark_read behavior, and an alternative HTTP endpoint. It omits nothing critical beyond what the schema already documents. The annotation contradiction tempers completeness slightly, but the description itself is quite thorough.

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?

Input schema covers all 5 parameters with descriptions (100% coverage), so baseline is 3. The description adds extra semantic value by giving a concrete type example ('sec_8k'), noting type and since can be combined ('and/or'), and explaining the effect of mark_read:true on subsequent calls.

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 clearly identifies the tool's output (recent alerts with source, citation_uri, raw payload) and distinguishes it from sibling tools by focusing on the alerts feed rather than changes or subscriptions.

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 states you can filter by type and since, and explicitly says polling works fine and the same feed is available via HTTP for scripts/dashboards, which implies the intended use case vs. external access. It doesn't explicitly name sibling tools to avoid, but provides clear contextual usage signals.

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