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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is clear. The description adds valuable behavioral context by explaining the mark_read side-effect (flags events read so subsequent calls show only newer ones), the returned fields (source, citation_uri, raw payload), and the availability of an HTTP endpoint. This 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 three sentences, front-loaded with the core purpose in the first sentence. Each sentence earns its place: the first describes what it does, the second details returned fields and filtering, and the third covers mark_read, polling, and the alternative endpoint. No redundant or filler content.

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?

For a 5-parameter tool with no output schema, the description covers the key aspects: what is returned (source, citation_uri, raw payload), how to filter, the mark_read behavior, and polling suitability. It doesn't describe the full response structure or error scenarios, but the provided information is sufficient for an agent to correctly invoke the tool in most cases.

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%, so the baseline is 3. The description rephrases filtering by type and since, and provides a concrete example ('sec_8k'), but this adds little beyond the schema's existing parameter descriptions. No additional syntax, defaults, or edge cases are introduced.

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 with a specific verb and resource: 'Pull fired events from your subscription feed' and 'Returns the most recent alerts'. This distinguishes it from sibling tools like list_subscriptions or recent_changes by focusing on the alert feed and the evaluator's persisted data.

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 gives usage context by noting 'Polls work fine' and provides an explicit alternative: 'the same feed is also at GET registry.pipeworx.io/alerts.json for scripts and dashboards.' This implies using this tool for agent interaction and the HTTP endpoint for automated scripts. However, it doesn't explicitly compare to sibling tools like recent_changes, leaving some ambiguity.

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