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

Annotations already convey readOnly, idempotent, non-destructive, and open-world behavior. The description adds meaningful behavioral context on top: the feed is persisted, the evaluator writes to it, mark_read flags events read on the same call, and unread_only filters on read_at. It also notes that the same feed is exposed at a public URL, which is useful for an agent deciding between polling this tool and using HTTP.

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?

Three sentences, front-loaded with what the tool returns, then filters, then read-state behavior, then polling note. Every sentence carries distinct information and there is no repetition of schema boilerplate.

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 read-only polling tool with no output schema, the description covers the key semantics an agent needs: what events are returned, how filters work, how read-state changes behavior, and an alternative URL for scripts/dashboards. It doesn't document pagination beyond a limit parameter or what the exact response shape looks like beyond the listed fields, but that's minor given the 100% schema coverage and the simplicity of the operation.

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 schema already documents all five parameters. The description adds only light semantic context (e.g., 'sec_8k' as an example for type, mark_read affecting the next call, since meaning fired_at >= the timestamp). That extra context is valuable but modest; a 3 baseline is fair when schema covers everything.

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?

States a specific verb ('Pull'), a specific resource ('fired events from your subscription feed'), and what the returned data carries (source, citation_uri, raw payload). It is clearly distinguishable from siblings like list_subscriptions (manage subscriptions) and recent_changes (different feed type).

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 says filtering by type and since, and polling is fine, plus points to an alternate access path (GET registry.pipeworx.io/alerts.json) for scripts. It does not name a sibling alternative to prefer for a given condition, but it gives enough context for an agent to know when to call it.

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