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

The annotation readOnlyHint=true suggests the tool is read-only, but the description discloses that mark_read:true mutates state by flagging returned events as read, affecting future calls. This is a direct contradiction with the annotation. Although the description itself is transparent, the contradiction forces a score of 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, front-loaded with the tool's purpose, and every sentence adds value. It covers returns, filtering, side effects, and alternatives without repetition or fluff, making it compact 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?

Despite lacking an output schema, the description explains the return content (source, citation_uri, raw payload) and key behaviors (persistence, filtering, mark_read, polling). It also mentions an alternative endpoint, giving a complete picture for a simple read/filter tool in a 5-parameter context.

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%, so all parameters are described. The description adds meaning by giving an example of type ('sec_8k'), specifying since as ISO timestamp, and explaining the behavioral effect of mark_read. This goes beyond the schema descriptions, providing practical usage clarity.

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 uses a specific verb ('Pull') and resource ('fired events from your subscription feed'), and clarifies the tool returns alerts the evaluator has written to a persisted feed. This clearly distinguishes it from siblings like list_subscriptions or recent_changes by focusing on event delivery with source and citation_uri.

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: filtering by type/since, using mark_read to manage state, and explicitly notes that polling works fine and provides an alternative REST endpoint for scripts/dashboards. Without naming sibling tools, it still offers usage-oriented guidance and an alternative, though it lacks explicit when-not-to-use instructions.

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