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

The annotations declare readOnlyHint=true and destructiveHint=false, indicating a safe, non-mutating read operation. However, the description states that setting mark_read:true will flag returned events as read and cause the next call to show only newer ones, which is a state-changing side effect. This directly contradicts the readOnlyHint annotation, making it a serious transparency issue.

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 well-structured and front-loaded with the primary purpose. Each sentence contributes information: return payload, filter options, mark_read side effect, polling note, and alternative access. It is a bit longer than necessary but remains concise and readable. No filler or repetition beyond the title, hence a 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?

Given the tool has 5 parameters and no output schema, the description thoroughly covers the return format (source, citation_uri, raw event payload), filtering, mark_read behavior, polling suitability, and an alternative REST endpoint for scripts. This is comprehensive and equips the agent with enough context to use the tool correctly. The contradiction with annotations is a flaw in annotation consistency, not in the completeness of the description itself.

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 covers all parameters (100% coverage), so the baseline is 3. The description adds meaningful context beyond the schema by explaining how parameters interplay: filtering by type (e.g., 'sec_8k'), since as an ISO timestamp, and the behavior of mark_read affecting future calls. It also notes default behavior (e.g., default false) implicitly. This added value warrants 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 the tool pulls fired events from the user's subscription feed and returns recent alerts. It uses a specific verb ('Pull') and resource ('fired events from your subscription feed'), distinguishing it from sibling tools like list_subscriptions and recent_changes by focusing on alerts the evaluator has written to the persisted 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 gives clear context on when to use the tool: to retrieve fired alerts from the feed, with optional filtering by type and since. It also mentions polling is fine and provides an alternative REST endpoint for scripts. However, it does not explicitly exclude other tools or compare with alternatives like list_subscriptions or recent_changes, hence not a 5.

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