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

The description explicitly documents a state-changing behavior: 'Set mark_read:true to flag returned events read so the next call only shows newer ones.' This directly contradicts the readOnlyHint=true annotation, which declares the operation as read-only. The description is transparent, but because it conflicts with the structured safety hint, it merits a score of 1 per the contradiction rule.

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 with zero fluff. It front-loads the core purpose, then packs in return fields, filter usage, mark_read side effect, polling guidance, and an alternative endpoint. Every sentence earns its place, and the structure is easy to scan.

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 read-only list tool, the description covers the essential operational details: response payload fields, filter mechanisms, the mark_read side effect, and polling suitability. It omits pagination specifics, but the limit parameter in the schema covers that gap. Overall, it is sufficiently complete to invoke the tool correctly, though a note on unread_only behavior would have been nice (already in 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 coverage is 100%, so the baseline is 3. The description adds meaningful value beyond the schema by giving an example filter value ('sec_8k'), explaining the semantic effect of mark_read (stateful flagging), and outlining what each returned event contains. This goes beyond simple field definitions and compensates for the lack of an output schema.

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 the specific verb+resource combination 'Pull fired events from your subscription feed,' and immediately clarifies the tool's scope (recent alerts, written by the evaluator). This clearly distinguishes it from siblings like list_subscriptions or recent_changes, which manage subscriptions or track changes rather than reading fired alerts.

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 provides practical usage context: 'Polls work fine' tells the agent that repeated polling is acceptable, and the alternative GET endpoint indicates when scripts/dashboards might prefer a different route. It does not explicitly name sibling tools or give exclusions, but the context is strong enough to imply when this tool should be used.

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