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

Annotations mark readOnlyHint=true, but description discloses that setting mark_read:true flags events as read, a side-effect. This adds behavioral context beyond annotations, though it may slightly contradict readOnlyHint.

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, no fluff, front-loaded with purpose. Efficiently conveys key information.

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?

Covers return fields, filtering, read state management, and alternative access. No output schema, but description gives enough structure for agent usage. Lacks explicit mention of default limit.

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% with detailed descriptions. Description adds an example for type ('sec_8k') but largely restates schema. Adequate but not significantly additive.

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 clearly states the tool pulls fired events from a subscription feed, specifying the verb 'pull' and resource 'fired events'. It distinguishes this from sibling tools like list_subscriptions by focusing on event retrieval.

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 usage context: filtering by type and since, using mark_read to manage read state, and mentions an alternative GET endpoint for scripts/dashboards. Does not explicitly exclude use cases but gives sufficient guidance for typical usage.

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