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

The description goes beyond annotations by detailing the return payload contents (source, citation_uri, raw event payload), the mark_read side-effect for subsequent calls, and polling behavior. It also states the feed is persisted. This adds value without contradicting the readOnlyHint, openWorldHint, idempotentHint, and destructiveHint 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 concise and well-structured: it opens with the core function, then explains return contents, then usage options, and finally additional context about polling and an alternative endpoint. No redundant words or filler; 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?

For a read-only tool with 5 parameters and no output schema, the description covers the essential aspects: what is returned, key filtering options, the mark_read side-effect, and the alternative feed URL. It doesn't explicitly detail 'limit' or 'unread_only', but these are adequately covered in the schema. It's sufficiently complete for an agent to 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?

With 100% schema description coverage, the schema already documents all parameters. The description adds contextual meaning, such as the example type 'sec_8k', the semantic of mark_read affecting next calls, and clarifying the 'since' filter as ISO timestamp with fired_at comparison. This supplements the schema with practical usage context.

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 verbs ('Pull', 'Returns') and a resource ('your subscription feed'). It also differentiates from siblings like recent_changes by emphasizing subscription alerts and the evaluator's persisted 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?

The description gives clear context for when to use the tool, such as polling and filtering by type and since, and notes that the same feed is accessible via a public URL. However, it does not explicitly mention alternatives or when NOT to use it, falling just short of the top bar.

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