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

The description discloses mark_read:true as a state-changing operation ('flag returned events read so the next call only shows newer ones'), contradicting the readOnlyHint:true annotation. Per rubric, this is an annotation contradiction, so the score is 1 despite the description's other useful behavioral details.

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 main action, then flows logically through return format, filtering, state mutation, and polling. Every sentence adds distinct information with no fluff or repetition.

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 what returned alerts contain (source, citation_uri, raw payload). Combined with full schema coverage for parameters and relevant annotations, the tool is well understood. It misses explicit mention of limit/unread_only, but the schema covers those.

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?

With 100% schema coverage, the baseline is 3. The description adds value by providing a concrete type example ('sec_8k'), clarifying that since is an ISO timestamp, and explaining the mark_read side effect, going beyond the schema descriptions.

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,' clearly identifying the action and resource. It further specifies the scope ('most recent alerts'), distinguishing it from sibling tools like list_subscriptions and subscribe/unsubscribe.

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?

It provides concrete usage context: filtering by type and since, setting mark_read, and polling. It also points to an alternative endpoint for scripts/dashboards, which helps with tool selection, though it doesn't explicitly name sibling tools to avoid.

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