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

Annotations already mark readOnly/openWorld/idempotent hint, so the bar is lower, but the description adds valuable behavior: the persistence of the feed, the mark_read effect on subsequent calls, and the polling-friendly nature. It clearly explains side effects (modifying read state) without contradicting the read-only annotation, since mark_read mutates read flags only.

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 sentences and every clause earns its place: what is returned, the payload contents, filtering, mark_read side effect, and alternative endpoint. It is front-loaded with the core action and remains highly readable.

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 no output schema, the description must convey return shape, and it does: source, citation_uri, raw event payload. It also covers all key parameters (type, since, mark_read) and mentions limit indirectly via query context, making it sufficiently complete for a tool with 5 optional parameters.

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 baseline 3. The description exceeds baseline by explaining the purpose of mark_read ('flag returned events read so the next call only shows newer ones') and gives a concrete type example ('sec_8k'), adding nuance beyond the schema descriptions.

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 opens with the specific verb 'Pull' and identifies the resource as 'fired events from your subscription feed.' It clearly distinguishes from sibling tools like list_subscriptions or recent_changes by describing the returned payload (source, citation_uri, raw event) and the filtering options.

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?

It gives clear context: polling works, and the feed is also available at a direct GET endpoint for scripts/dashboards. This implies the tool is suitable for interactive/Agent use while the endpoint is for automation. However, it does not explicitly state when to choose this over a sibling tool like recent_changes or list_subscriptions, only the alternative HTTP access.

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