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

Beyond annotations, the description explains the mark_read side effect (flags events as read, affecting future calls), the persisted feed nature, and the return payload structure. This adds valuable behavioral context without contradicting the readOnlyHint/idempotentHint 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 compact yet information-dense, front-loaded with the core purpose, then details each key aspect in separate sentences. Every sentence earns its place, and the alternate endpoint is tacked on without bloating the core message.

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?

With no output schema, the description compensates by listing the return payload fields. It covers filtering, mark_read side effects, polling, and an alternative access method, making it complete for a read-only list tool with 5 parameters.

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 with a concrete type example (sec_8k) and explains the semantic effect of mark_read, which is not fully captured in the schema. However, it does not elaborate on limit or unread_only, so it stops short of a 5.

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, with specific return details (source, citation_uri, raw payload). It distinguishes itself from siblings like list_subscriptions and recent_changes by focusing on the alert feed.

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?

Provides explicit usage context: filtering by type and since, mark_read behavior, and an alternative endpoint for scripts/dashboards. The phrase 'Polls work fine' directly addresses polling, and the mention of the HTTP endpoint gives a clear alternative.

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