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

Beyond the readOnly/openWorld/idempotent annotations, the description reveals that events carry source, citation_uri, and raw payload, and that mark_read:true mutates read state so subsequent calls return only newer events. It also mentions persistence and the public mirror endpoint, adding substantive behavioral context with no contradiction.

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 dense sentences front-load the core purpose, then filter options, then operational guidance. Every sentence contributes new information; no filler or repetition.

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 compensates by specifying the key fields in each returned alert and explaining filter/read-state behavior. It also addresses operational concerns (polling, alternative endpoint), making the tool self-sufficient for an agent despite five 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 covers all five parameters, so baseline is 3; the description adds value by giving a concrete type example ('sec_8k'), clarifying since as an ISO timestamp, and explaining the semantic consequence of mark_read ('next call only shows newer ones'). This goes beyond the schema without restating it.

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 'Pull fired events from your subscription feed,' naming a specific action and resource. It further details the return contents (source, citation_uri, raw payload) and distinguishes this from general tools by focusing on the evaluator's persisted alert feed.

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 explains that polling works fine and points to an alternative HTTP endpoint for scripts/dashboards, providing clear usage context. It does not explicitly enumerate when to use this over sibling tools like recent_changes, but the feed-specific language implies the appropriate scenario.

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