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

With no annotations, the description carries a heavier burden. It discloses important behavior: returns a delta of breaking items with age/expiry and should be polled with a since cursor. It does not detail auth/rate limits or exact response shape, which a full dialogue would still need.

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?

Two dense sentences and no wasted words. The description front-loads the core resource and then provides the integration pattern, making it highly readable and actionable.

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 simple two-parameter tool without an output schema, the description covers the essential task, return content concept, and polling pattern. It lacks a precise indication of the response format or how expiry is represented, but is otherwise complete enough to proceed.

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?

The description adds meaning to the 'since' parameter by recommending its use as '{last generated_at}' for polling deltas. Schema coverage is only 50%, but this definition compensates for the most significant parameter; 'limit' remains under-described but is inferable.

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 defines the tool's resource scope: 'active alerts plus breaking-flagged articles with age and expiry.' It distinguishes this from general asha feed/digest tools, though it lacks an explicit action verb like 'list' or 'retrieve.'

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 explicit usage context: 'Poll every 60s with since={last generated_at} for deltas; notify your user on new items.' This is strong operational guidance, but it stops short of contrasting with sibling tools or stating when not to use this tool.

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