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

The description states setting mark_read:true flags events as read, implying mutation. However, annotations declare readOnlyHint=true, indicating no state modification. This is a direct contradiction, severely harming transparency.

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, structured with a clear purpose first, followed by key features and alternatives. Every sentence adds meaningful information without redundancy.

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?

Despite no output schema, the description details return fields (source, citation_uri, payload) and covers all parameters. It also addresses polling behavior and provides an alternative REST endpoint, making it self-contained for agent usage.

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 value by giving examples (e.g., 'sec_8k' for type, ISO timestamp for since) and explaining mark_read's effect, which goes beyond the schema's minimal 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 the tool pulls fired events from the subscription feed, specifying it returns recent alerts with source, citation_uri, and raw payload. It distinguishes from siblings like list_subscriptions by focusing on alert events.

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 polling works fine and points to a REST API alternative for scripts/dashboards. It provides guidance on using mark_read for state management but does not explicitly exclude other use cases or mention when to use alternative tools.

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