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

Annotations declare readOnlyHint:true, but the description instructs that setting mark_read:true 'flag[s] returned events read so the next call only shows newer ones,' which is a state-mutating side effect. This directly contradicts the readOnlyHint annotation. Per rubric, this is an annotation contradiction, and the description fails to disclose the state change.

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?

Four sentences, each with a distinct purpose: purpose, return payload, filtering/read flag, and polling/alternative access. No fluff, front-loaded with the verb. Ideal size and structure.

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?

For a tool with no output schema, the description explicitly describes the return payload (source, citation_uri, raw event payload). It explains mark_read side effects and provides an alternative access method. It omits nothing essential for basic invocation, though it doesn't discuss unread_only or limit defaults (covered by schema).

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 covers all parameters with descriptions (100% coverage), so baseline is 3. The description adds valuable meaning for mark_read (explaining the consequence for subsequent calls) and clarifies since and type usage. It doesn't repeat the schema's numeric ranges but adds semantic context for behavior.

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,' a specific verb+resource statement that clearly states the tool's function. It distinguishes this tool from siblings like list_subscriptions (managing subscriptions) and recent_changes (change feed) by focusing on alerts from the persisted feed. The phrase 'Returns the most recent alerts the evaluator has written to your persisted feed' further clarifies the scope.

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 mentions that 'Polls work fine' and suggests an alternative HTTP endpoint for scripts/dashboards, giving implementation guidance. It also explains when to set mark_read:true to change subsequent call behavior. However, it doesn't explicitly contrast with sibling tools like recent_changes, leaving some ambiguity for an agent deciding between them.

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