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

The description discloses a side effect: 'Set mark_read:true to flag returned events read so the next call only shows newer ones,' which changes persistent feed state. This directly contradicts the annotations' readOnlyHint=true. The contradiction is a serious inconsistency, so the score is 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 front-loaded with the core purpose and then covers return items, filtering, mark_read, polling, and an alternate endpoint. It is about five sentences and each adds useful information, though the external URL could be considered slightly tangential. No bloat, so 4.

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 explains return contents (source, citation_uri, raw payload), filter options (type/since), the mark_read side effect, and polling suitability. It also points to a public feed URL. While it doesn't explicitly describe the exact response shape, no output schema exists, and the listed info is sufficient for practical use. Minor gaps like unread_only/limit are covered by the schema, so 4.

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?

The input schema already covers all parameters with descriptions, so baseline is 3. The tool's description adds value by giving a concrete type example ("sec_8k"), clarifying that 'since' takes an ISO timestamp, and explaining the behavior of mark_read. These enrich the parameter semantics beyond the schema.

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,' which clearly states the tool's specific action and resource. It also distinguishes itself from siblings like list_subscriptions and recent_changes by focusing on fired alerts and the evaluator's feed.

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: for polling the feed, filtering by type/since, and marking events read. It also mentions an alternative URL for scripts/dashboards. However, it does not explicitly name alternatives among sibling tools or specify when not to use it, stopping 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.