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

Annotations declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint as false. The description adds that setting mark_read:true flags events as read, affecting subsequent calls, which is a behavioral nuance beyond annotations. It also notes that polling works fine, implying no side effects.

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 at 4 sentences, front-loading the core purpose. Every sentence adds value: purpose, key fields, filtering options, behavioral note, and alternative access method. No fluff.

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?

Although there is no output schema, the description explicitly lists the fields returned (source, citation_uri, raw event payload). It covers input parameters, behavioral options, and even mentions alternative access for scripting, making it fully self-contained.

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% with descriptions for all 5 parameters. The description enriches these by providing examples (e.g., 'sec_8k' for type, ISO timestamp for since) and explaining the side effect of mark_read:true. This adds practical meaning beyond the schema alone.

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 'Pull fired events from your subscription feed,' clearly specifying the verb and resource. It distinguishes the tool by focusing on subscription feed events, unlike sibling tools like list_subscriptions or recent_changes.

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 explains filtering by type and ISO timestamp, and the mark_read option for stateful polling. It also mentions that the same feed is available at an alternative endpoint for scripts/dashboards, providing context for when to use this tool vs. direct API access. However, it does not explicitly contrast with sibling tools.

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