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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable context about the returned payload structure (source, citation_uri, raw event payload) and discloses that mark_read:true flags events as read, which is a mild state-changing behavior. This transparency about the optional side-effect goes beyond the annotations without contradicting them.

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 compact (three sentences) and well-structured: it states the core purpose, describes the return payload, covers filtering options, explains the mark_read behavior, and notes a non-MCP alternative. Every sentence adds value with no wasted words.

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 has 5 parameters, no output schema, and good annotations, the description is complete. It explains the return format (each alert carries source, citation_uri, and raw event payload), the filtering capabilities, the mark_read semantics, and even provides an HTTP endpoint for scripts. This covers all essential aspects for an agent to use the tool effectively.

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 description coverage is 100% with per-parameter descriptions, so baseline is 3. The description enhances this by giving a concrete filter example (type "sec_8k") and explaining the practical effect of mark_read ('flag returned events read so the next call only shows newer ones'). This adds semantic depth beyond the schema's bare 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 clearly states the tool's function: 'Pull fired events from your subscription feed. Returns the most recent alerts the evaluator has written to your persisted feed.' It specifies the resource (subscription feed alerts) and the action (pull/return), and distinguishes it from siblings like list_subscriptions, which lists subscriptions rather than alert events.

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 provides clear context on when to use the tool: for polling recent alerts, filtering by type/since, and using mark_read to control visibility. It also mentions an alternative access method (GET registry.pipeworx.io/alerts.json) for scripts and dashboards, but does not explicitly compare against sibling MCP tools or state when not to use them. It gives good context without formal exclusions.

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