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

Annotations indicate read-only and idempotent behavior, but the description adds important context: mark_read mutates read state to affect subsequent calls, and the same feed is available at a public URL. This goes beyond the annotations without contradicting them, though the mark_read side effect is slightly at odds with the 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?

The description is three focused, well-structured sentences. Each sentence adds value: purpose, capabilities, and behavior are all delivered without redundancy or filler.

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 list-style tool with no output schema, the description is remarkably complete: it explains the return payload, filtering options, mark_read state behavior, polling suitability, and alternative access. With annotations covering the safety profile, no critical information is missing.

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?

The schema fully covers all five parameters, but the description adds real-world meaning with a concrete type example ('sec_8k'), clarifies the ISO timestamp format, and explains mark_read's side effect. This enhances understanding beyond the schema definitions.

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, specifying the return payload (source, citation_uri, raw event) and distinguishing it from sibling tools like list_subscriptions and subscribe by focusing on alert 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 explicit guidance on filtering by type and since, using mark_read to control future reads, and notes that polling works. It also offers an alternative HTTP endpoint for scripts/dashboards, giving context for when the tool is appropriate, though it doesn't explicitly state when not to use it.

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