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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real value on top: result ordering (newest first), the shape of each item (id, timestamp UTC, type, tool, summary, link, verification), the `next_since` cursor contract for polling, and a security warning that field-report text is untrusted. That last point is a genuine prompt-injection disclosure an agent could not infer from any structured field.

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?

Roughly 60 words, front-loaded with the resource and ordering, then event types, then item shape, then polling, then endpoint equivalence, then the untrusted-content caveat. Every clause contributes a distinct fact; nothing is repeated from the title or annotations.

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 usefully documents the per-item fields and the next_since cursor, which an agent needs to paginate. What remains thin is the filtering surface: the meaning of the `tool` filter pattern and the `limit` default/max are not addressed, and there is no note on result truncation behavior at limit=500.

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 50%: `type` and `since` already carry schema descriptions, and the description's event-type list merely mirrors the `type` enum values. The polling advice adds meaning to `since` (use next_since from the prior call), but `tool` and `limit` receive no explanation in either the schema or the description, so it does not fully compensate for the coverage gap.

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?

Opens with a specific question the tool answers ('What changed on Agent Tested, newest first') and enumerates the concrete event types it surfaces (new_tool, retest, verdict_change, warning, retest_queued, field_report). No sibling in the list is a change feed, so it is trivially distinguishable from search_tools, list_lab_queue, or check_outages.

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?

Gives a clear usage pattern: 'Poll cheaply with since set to next_since from your last call,' which tells the agent how to do incremental polling rather than re-fetching everything. It stops short of stating when NOT to use it (e.g., when a full tool snapshot via get_tool is more appropriate), so it is strong context without explicit exclusions.

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