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

The description discloses key behavioral traits beyond the annotations, such as the persisted feed behavior and the mark_read side effect ('Set mark_read:true to flag returned events read so the next call only shows newer ones'). This adds valuable context about state changes that the annotations alone do not convey. It does not contradict the readOnlyHint, as the default behavior remains read-only and the state change is opt-in.

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 at five sentences, each serving a distinct purpose: stating the core function, describing the return value, explaining filtering, clarifying mark_read behavior, and noting polling/HTTP alternatives. It is front-loaded with the primary action and contains no fluff 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?

Despite having no output schema, the description explains the return fields (source, citation_uri, raw payload) and covers the main usage scenarios. It addresses state-changing behavior, filtering options, and even provides an external mirror URL. This is remarkably complete given the tool's complexity and the rich schema.

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?

The schema covers all 5 parameters with descriptions (100% coverage), so the baseline is 3. The description adds extra meaning by providing a concrete type example ('sec_8k'), clarifying the consequence of mark_read, and explaining what the returned payload contains. This enriches the parameter understanding beyond the schema.

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.' It specifies the resource (subscription feed), the action (pull/return alerts), and the scope (most recent alerts). It distinguishes from sibling tools like list_subscriptions or subscribe by focusing on reading fired events, not managing subscriptions.

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 for when to use the tool, noting that 'Polls work fine' and offering an alternative HTTP endpoint for scripts/dashboards. However, it does not explicitly mention when not to use it or name alternative MCP tools, so it stops short of fully explicit exclusions.

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