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

Annotations already cover read-only, open-world, idempotent, and non-destructive aspects. The description adds important behavior beyond annotations: the mark_read flag causes an internal state change (only newer events appear next call), and polling is fine, which is not implied by the annotations. This gives useful context without contradiction.

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 five sentences, each earning its place: main action, return format, filtering, mark_read behavior, and polling/alternate access. It is front-loaded with the core purpose, and every sentence adds distinct information without padding 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 fully explains the return payload (source, citation_uri, raw event), the filtering options, the state change semantics of mark_read, and the alternative HTTP access. Combined with rich annotations, the agent has all necessary context to invoke this tool safely and 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?

The input schema covers all parameters with descriptions (100% coverage), establishing a baseline of 3. The description adds value by giving a concrete example for type ("sec_8k"), clarifying that since expects an ISO timestamp, and explaining the consequence of mark_read (subsequent calls return only newer events). These enrich the schema's otherwise terse definitions.

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 opens with a specific verb ('Pull') and resource ('fired events from your subscription feed'), clearly distinguishing this from siblings like recent_changes or list_subscriptions. It further specifies the return contents (source, citation_uri, raw payload), leaving no ambiguity about the tool's function.

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 use: retrieving recent alerts from the feed, with optional filters and polling behavior explicitly deemed acceptable. It also points to an alternative HTTP endpoint for scripts/dashboards, but does not explicitly contrast against sibling MCP tools, which prevents a 5.

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