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

Annotations already indicate read-only (readOnlyHint=true) and idempotent (idempotentHint=true). The description adds useful behavioral details: it explains that setting mark_read:true flags events as read, affecting future calls, and that polls work fine. It also discloses the return format (source, citation_uri, raw event payload). No contradictions with annotations.

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 with no wasted sentences. It front-loads the core purpose and then lists key features, filtering options, and an alternative access method. While it is somewhat dense, every sentence adds value. It could be slightly shorter but is well-structured.

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 that there is no output schema, the description adequately explains what is returned (source, citation_uri, payload). It accounts for all parameters, annotations, and common usage patterns. The tool is simple and read-only, so no additional behavioral details are needed. The description feels complete for its complexity level.

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 the schema already documents all parameters. The description adds practical context: explains the effect of mark_read, specifies the default and range for limit (1-200, default 50), clarifies that since is an ISO timestamp, and explains unread_only filters on read_at null. This goes beyond the schema's brief 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 starts with a clear verb-resource pair: 'Pull fired events from your subscription feed.' It specifies the action (pull), the resource (alerts from subscription feed), and distinguishes itself from sibling tools like 'subscribe' (which manages subscriptions) and 'list_subscriptions' (which lists them). The scope is explicit: 'most recent alerts.'

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?

The description explains when to use the tool: for polling and retrieving alerts. It provides filtering options and mentions an alternative method ('the same feed is also at GET registry.pipeworx.io/alerts.json for scripts and dashboards'). However, it does not explicitly state when not to use it or compare with siblings like 'recent_changes'.

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