poll_feed

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

The description discloses the outputs ('what was added, denied, and the safety gate decision'), which gives some behavior insight, but without annotations, it fails to clarify potential side effects, rate limits, or state modifications. The term 'poll cycle' may imply destructive marking of items, which is not addressed.

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 concise at one sentence and front-loaded with purpose. It avoids fluff, but could incorporate parameter information without losing its lean structure.

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 provides a high-level overview of outputs but lacks detail on format or structure. It is adequate for understanding the tool's role but not sufficient for precise invocation without additional context from the agent's knowledge of similar tools.

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 description does not mention the max_items parameter, and schema description coverage is 0%. However, the parameter name and constraints (min, max, default) are self-explanatory. A brief mention in the description would have been helpful but is not critical.

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 action ('Run a single poll cycle') and the resource ('the feed'), but does not differentiate from sibling tools like 'get_feed' or 'build_digest', which also deal with feed content.

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?

No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, context, or when polling is appropriate over other feed-related tools.

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