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

The description states 'Set mark_read:true to flag returned events read,' a state-changing side effect. This contradicts the annotation readOnlyHint:true, which declares the tool read-only. Even though the description discloses the behavior accurately, the annotation conflict forces a score of 1 per the rules.

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?

Three sentences, front-loaded with the primary purpose, then filters and alternative access. No unnecessary detail or repetition; every sentence adds value.

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?

With no output schema, the description explains return fields (source, citation_uri, raw event payload) and read-tracking behavior, plus provides an HTTP alternative. Minor omissions like empty-response behavior or interaction between unread_only and mark_read are acceptable given the tool's simplicity.

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 5 parameters with descriptions, but the prose adds meaningful context: explains that since filters by fired_at time, and that mark_read causes returned events to be marked read so subsequent calls return only newer ones. This goes beyond the schema's basic type/description.

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 and resource. It clearly differentiates from siblings like list_subscriptions by focusing on fired alerts rather than subscription management, and enumerates returned fields.

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?

Provides clear usage context: 'Polls work fine' and mentions the same feed is available via HTTP for scripts/dashboards. It doesn't explicitly exclude sibling tools or state 'when not to use,' but the polling and read-tracking guidance gives practical direction.

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