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

Annotations already indicate read-only, idempotent, non-destructive. Description adds the side-effect of mark_read:true (flags events read, so subsequent calls skip them), which is beyond what annotations convey. 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?

Reasonably concise, with the core purpose front-loaded. Each sentence adds value, though one could argue slight redundancy between 'watch' description and parameter details. Not overly verbose.

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?

No output schema, so description compensates by detailing return fields (source, citation_uri, payload). Covers filtering, mark_read side-effect, and alternative access method. Adequate for a read-only list tool with good annotations.

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 brief descriptions. The tool description adds practical context: filter examples ('sec_8k'), ISO timestamp requirement, and the effect of mark_read on next call. This enhances understanding beyond schema alone.

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 uses a specific verb ('Pull') and resource ('fired events from your subscription feed'), clearly distinguishing it from sibling tools like recent_changes or search_within. It enumerates key fields returned (source, citation_uri, payload), making the tool's role unambiguous.

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?

States that polling works fine and points to an alternative HTTP endpoint for scripts/dashboards, offering context on when to choose this tool. Missing explicit when-not or comparisons to sibling tools, but the alternative mention is helpful.

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