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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds important behavioral context: mark_read flags events as read for subsequent calls, and the feed is persisted. No contradictions.

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, front-loaded with the main action, no fluff. Every sentence adds necessary detail.

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?

Given read-only nature, full parameter coverage in schema, and no output schema, the description explains return value structure, filtering options, polling suitability, and alternative access. Complete for the domain.

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 has 100% description coverage, so baseline is 3. The description adds value with examples (e.g., 'sec_8k' for type) and clarifies the side-effect of mark_read. This justifies a 4.

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 what it returns (source, citation_uri, payload) and how to filter. It distinguishes from sibling tools that manage subscriptions or perform other actions.

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 context for usage: polling is fine, filtering by type and timestamp, and mentions an alternative external endpoint. It lacks explicit when-not-to-use or direct sibling differentiation, but is clear enough for typical use.

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