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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint (false). The description adds behavioral details beyond annotations: it explains the effect of mark_read (flagging events read so next call is newer), the return fields, and that the feed is persisted. No contradiction with 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?

Five sentences, each serving a distinct purpose: purpose, return details, filtering, mark_read effect, alternative access. No fluff, front-loaded with primary action. Every sentence earns its place.

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?

Given 5 parameters, all described in schema, the description covers key aspects: return fields (no output schema but mentioned), filtering, and mark_read. It might miss ordering or default limit behavior, but for a simple polling tool, it is complete enough.

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 an example for type ('sec_8k'), explaining mark_read semantics, and specifying ISO timestamp for since. However, it does not mention the unread_only parameter in the description, though the schema covers it. Overall, it adds meaningful context beyond 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 clearly states it pulls fired events from a subscription feed, with specific verb 'Pull' and resource 'fired events from your subscription feed'. It mentions return fields (source, citation_uri, raw payload). However, it does not explicitly differentiate from sibling tools like list_subscriptions or subscribe, leaving a slight gap in distinguishing 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 context for use: filtering by type and since, and notes that polls work fine. It also mentions an alternative access method (GET endpoint). However, it gives no explicit guidance on when not to use this tool vs siblings, or prerequisites (e.g., needing a subscription).

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