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 changes state on the feed. This directly contradicts the annotation readOnlyHint:true, which marks the tool as read-only. Therefore, the description contradicts the annotation, and per rubric, behavioral transparency must be score 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 4 sentences, front-loaded with the primary purpose, then return values, filtering, and additional notes. Each sentence adds new information without fluff, earning a 5.

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?

The description covers the return fields, filtering options, mark_read side effect, polling behavior, and an alternative HTTP endpoint. It lacks explicit pagination or error details, but given the schema and annotations, it's largely complete.

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?

With 100% schema coverage, the baseline is 3. The description adds extra value beyond the schema by explaining the practical use of type (e.g., 'sec_8k') and the effect of mark_read on subsequent polls. It does not cover unread_only or limit in detail but the schema covers them, so a 4 is justified.

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 'Pull fired events from your subscription feed,' a specific verb+resource combination that clearly distinguishes it from sibling tools like list_subscriptions or recent_changes. It further specifies the return payload (source, citation_uri, raw event) and the data origin ('alerts the evaluator has written').

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 context for when to use the tool: it mentions filtering by type/since and that 'Polls work fine,' implying it is suitable for repeated retrieval. It also points to an alternative method for scripts and dashboards (the GET endpoint), enriching usage context, though it does not explicitly name sibling tools or state when not to use them.

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