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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false, and the description adds behavioral context beyond these: it explains the feed is written by the evaluator, describes the returned fields (source, citation_uri, raw payload), and clarifies that mark_read causes future calls to exclude read events. This goes well beyond the annotation flags, giving the agent a clear model of state changes despite being read-only.

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 four sentences, each adding distinct value: the first states the core action, the second describes the output shape, the third covers filtering and mark_read, and the fourth provides an alternative access method. It is front-loaded and free of redundant phrasing.

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 list tool with 5 optional parameters and no output schema, the description covers the primary use case, the behavioral semantics (mark_read), filter options, and even an alternative endpoint. The schema covers parameters and defaults, so the description need not repeat them. It's complete enough for an agent to select and invoke correctly.

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 schema already describes all 5 parameters with 100% coverage, so the baseline is 3. The description adds a concrete type example ('sec_8k') and explains the consequence of mark_read ('the next call only shows newer ones'), which enriches the schema's description. Since the added value is modest but present, a 4 is appropriate.

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 uses a specific verb ('Pull') and clearly identifies the resource ('fired events from your subscription feed'). It also distinguishes this from siblings by focusing on reading alerts, as opposed to subscribing/unsubscribing (subscribe, unsubscribe) or recent_changes. The mention of the alert payload components further clarifies its scope.

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 clear usage context: it's for fetching recent alerts from the persisted feed, supports filtering by type and time, and explains mark_read behavior. It also mentions polling and an alternative HTTP endpoint for scripts/dashboards, which gives a clear sense of when to use this tool vs. alternatives. It doesn't explicitly exclude other tools but the context is sufficient.

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