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

Beyond annotations (readOnlyHint, idempotent, non-destructive), the description adds behavioral context: setting mark_read:true flags events as read so subsequent calls show only newer events. It also describes return fields (source, citation_uri, raw payload) and mentions the feed is persisted.

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 with no redundant words, front-loaded with the main action and key features. Every sentence adds value, covering purpose, return content, filtering, marking read, and alternative access.

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?

Despite no output schema, the description covers return fields (source, citation_uri, raw payload) and provides context about polling and an alternative REST endpoint. For a read-only feed tool with good annotations, this is highly complete.

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 coverage, baseline is 3, but the description adds significant value: provides an example for type ('sec_8k'), specifies ISO timestamp for since, and explains the effect of mark_read. This goes beyond the schema's brief descriptions.

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 a subscription feed, with specific verb 'Pull' and resource 'recent alerts'. It distinguishes from siblings like list_subscriptions by specifying it returns alerts with source, citation_uri, and raw payload, focusing on recent events.

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 explains filtering by type and since, and mentions that polling works fine, with an alternative REST endpoint for scripts/dashboards. However, it does not explicitly state when to use this tool versus other tools like subscribe or list_subscriptions, or when not to use it.

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