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

The description explicitly states that setting mark_read:true 'flag[s] returned events read' and changes future call results, which is a state mutation. This directly contradicts the annotation readOnlyHint=true (and arguably idempotentHint=true when mark_read is used). This is an annotation contradiction.

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?

Front-loaded with the action, and each sentence adds something (return payload, filtering, mark_read semantics, polling/endpoint note). Some redundancy between 'Pull' and 'Returns' and the extra endpoint URL are minor, so not quite a 5.

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 5-param optional-parameter tool with no output schema, the description covers the return item shape, filter usage, mark_read behavior, and polling/alternate endpoint. It is largely complete, though the annotation contradiction undermines trust in its behavioral accuracy.

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?

Input schema has 100% description coverage for all 5 parameters. The description adds examples and the mark_read side effect, but those are already present in the schema; it does not meaningfully reduce ambiguity beyond the baseline.

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?

Opens with a specific verb and resource ('Pull fired events from your subscription feed') and explicitly describes what is returned (source, citation_uri, raw event payload). This clearly distinguishes it from siblings like list_subscriptions and recent_changes.

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?

Gives clear usage context: it is for polling fired alerts, supports filtering by type/since, and notes that the same feed is available at a URL for scripts/dashboards. It does not explicitly exclude alternatives or mention sibling tools, but the context is sufficient.

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