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

The description contradicts the annotation readOnlyHint=true by explaining that setting mark_read:true flags events as read and that the next call only shows newer ones. This is a persistent state mutation, not purely read-only. Therefore the description directly contradicts a structured annotation, and the transparency score must be 1 per the rubric.

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 three sentences and front-loaded with the core purpose. It includes useful details about return payload and filtering, plus an alternative access URL. Every sentence contributes meaning, though the final URL sentence is somewhat tangential to using the tool itself. Still, it is 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?

With five parameters and no output schema, the description covers the expected return values (source, citation_uri, payload), the mark_read side effect, and the polling use case. It also mentions the parallel HTTP endpoint, which aids context. The only significant gap is the annotation contradiction, but structure and content are otherwise complete enough for an agent to use the tool correctly.

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 description coverage is 100%, so the baseline is 3. The description adds a concrete example for type ("sec_8k"), explains the since parameter (ISO timestamp), and clarifies the side effect of mark_read. However, it does not add meaningful semantics for limit or unread_only beyond the schema, so it stays at the baseline.

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 starts with 'Pull fired events from your subscription feed,' which is a specific verb+resource pairing. It clearly distinguishes this from siblings like list_subscriptions (list subscriptions) and recent_changes (changes to something else), and it details what each alert contains (source, citation_uri, raw payload).

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 gives clear context: it is for pulling fired events, filtering by type/since, and marking as read. It explicitly mentions that polling works fine and points to an alternative HTTP endpoint for scripts/dashboards. However, it does not explicitly compare to sibling tools or state when not to use this tool, so it lacks exclusionary guidance.

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