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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds important context: setting mark_read:true mutates read state so future calls return only newer events, and that polling is safe. It also mentions the external URL for the same feed, which is extra behavioral context not in 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 compact and front-loaded with the main action. All sentences provide useful information—return structure, filtering, side effects, and an alternative access method. It is slightly longer than strictly necessary but avoids redundancy and stays focused.

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?

With no output schema, the description adequately covers return contents (source, citation_uri, payload) and key behaviors. It also explains mark_read semantics and provides an external access option. Gaps such as error handling or pagination parameters are not covered, but for this tool's complexity the description is sufficiently complete.

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 already covers 100% of parameters with descriptions. The description adds extra semantic value by giving a concrete example for 'type' (sec_8k), explaining the effect of 'mark_read' (flags events as read and affects subsequent calls), and clarifying that 'since' uses ISO timestamps. This goes beyond the schema's basic 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 what the tool does: 'Pull fired events from your subscription feed' and specifies the return contents (source, citation_uri, raw event payload). It distinguishes itself from siblings like recent_changes by focusing on subscription alerts and referring to 'the evaluator has written to your persisted feed'.

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 explicitly mentions that polling is acceptable and provides an alternative: 'the same feed is also at GET registry.pipeworx.io/alerts.json for scripts and dashboards.' This gives clear guidance on when to use the tool versus the HTTP endpoint. It also explains filtering by type and since, and the mark_read option for incremental reads.

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