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

Annotations declare readOnlyHint=true, implying no data modification. The description, however, explicitly states that setting mark_read:true 'flag[s] returned events read so the next call only shows newer ones', which is a mutation of the feed state. This is a direct contradiction between description and annotations, severely undermining transparency.

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 remarkably concise: three sentences that cover purpose, return format, filtering, and polling behavior. Every sentence adds value with no redundancy. The paragraph is front-loaded with the core action and then efficiently expands on specifics.

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 the tool's simplicity and the absence of an output schema, the description adequately covers return fields (source, citation_uri, payload), all parameters (type, since, mark_read, unread_only, limit), and behavioral notes (polling, alternative endpoint). No critical information is missing for an agent to use this tool correctly.

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%, but the description adds meaning beyond the schema: it explains the effect of mark_read (flags read to exclude from next call) and clarifies that unread_only returns events with null read_at. These details help the agent understand parameter behavior beyond the schema's terse 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 ('Pull') and resource ('fired events from your subscription feed'), specifying return fields (source, citation_uri, raw event payload). It distinguishes itself from sibling tools like 'list_subscriptions' and 'subscribe' by focusing on alert retrieval, and even mentions an alternative REST endpoint for scripts/dashboards, clarifying its role within MCP.

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 states 'Polls work fine', indicating suitability for polling scenarios, and notes the same feed is available at a REST endpoint (GET registry.pipeworx.io/alerts.json) for scripts and dashboards, offering an alternative. However, it does not explicitly exclude usage in other contexts or compare with siblings for when not to use.

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