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

The description discloses the key behavioral trait of optionally marking events as read via mark_read, which is a state change. However, this contradicts the annotation readOnlyHint=true, which implies no state modification. The description adds important context that annotations fail to capture, hence a 4 but with an annotation contradiction flagged.

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, front-loaded with the core action, and each sentence adds value. No redundancy or filler. Perfectly concise for the information provided.

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?

Despite lacking an output schema, the description explains return fields (source, citation_uri, raw event payload). It covers all parameters, provides use-case guidance (polling, alternative endpoint), and gives sufficient context for an agent to use the tool correctly. No gaps.

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%, baseline 3. The description adds meaning by explaining that type and since are filters, limit controls max events, mark_read flags events as read, and unread_only is implied. It provides use-case context beyond the schema, such as 'Polls work fine' and the alternative endpoint, justifying 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 'Pull fired events from your subscription feed' and details the returned fields (source, citation_uri, raw event payload). It distinguishes itself from sibling tools by providing a specific verb and resource, though no direct sibling for alerts exists. The description is specific and unambiguous.

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 explicit guidance on when to use the tool: filter by type and/or since ISO timestamp, use mark_read to acknowledge events, and notes that polling works fine. It also mentions an alternative GET endpoint for scripts/dashboards, giving clear usage context and exclusions.

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