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

Annotations already indicate a safe, read-only, idempotent operation. The description adds important behavioral context beyond annotations: it discloses that setting mark_read:true modifies state by flagging events as read, affecting subsequent calls. It also reveals the return payload structure and the availability of an HTTP mirror, adding transparency without contradicting the annotations.

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, each earning its place. The purpose is front-loaded, followed by return details, filtering, and a usage tip with an alternative. No redundant or vague wording.

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 covers return values (source, citation_uri, raw payload), filtering, side effects (mark_read), and even mentions an alternate access method. It is complete for a feed-pulling tool, leaving no major operational gaps.

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 goes beyond by providing an example for type (sec_8k), specifying the ISO timestamp format for since, and explaining the side effect of mark_read:true. This enriches the schema, though unread_only and limit remain only in the 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 clearly states the tool pulls fired events from the subscription feed and returns the most recent alerts. It specifies the verb 'pull' and the resource, and distinguishes itself from siblings like list_subscriptions by focusing on alerts rather than subscription management.

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 clear usage context, including filtering options, mark_read behavior, and notes that polling works fine. It also mentions an alternative HTTP endpoint for scripts/dashboards, which serves as an explicit alternative for different use cases. It lacks explicit 'when-not-to-use' guidance, but the niche is well-defined.

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