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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint as true/true/true/false, indicating safe, repeatable reads. The description adds useful behavioral details: the effect of mark_read on subsequent calls, the nature of the feed as persisted, and the data returned (source, citation_uri, raw payload). It does not disclose any negative behaviors but provides solid context beyond 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 concise (4 sentences) and front-loaded with the core purpose. Every sentence adds value, covering the return data, filtering options, mark_read behavior, and a note on alternative access. No superfluous information.

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?

Given no output schema, the description explains the return values (source, citation_uri, raw payload) and notes the feed is persisted. It covers key usage patterns (polling, filtering, mark_read). It does not mention error cases, rate limits, or maximum limit range (though that is in the schema). Overall, fairly complete for a tool with good annotations.

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 coverage is 100%, so baseline is 3. The description adds meaning by explaining the purpose of filtering by type and since, and notably clarifies the mark_read parameter (flagging events read so next call shows newer). It does not detail limit or unread_only, but the schema already covers their descriptions. The added context justifies a slightly higher score.

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 purpose: pulling fired events from a subscription feed and returning recent alerts. It specifies what each alert contains (source, citation_uri, raw payload) and distinguishes itself from other tools by focusing on alerts from the persisted feed, which is distinct from sibling tools like 'ai_visibility_check' or 'ask_pipeworx'.

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 good context, including filtering options (type, since, mark_read) and mentions that polling is acceptable. It also points to an alternative REST endpoint for scripts/dashboards. However, it lacks explicit guidance on when not to use this tool versus alternatives, such as when to use search_within or other retrieval tools.

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