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

Despite annotations indicating read-only, the description discloses that mark_read:true mutates the feed's read state, a side effect beyond what annotations imply. It also explains polling behavior and the persisted-feed nature, providing valuable behavioral context that annotations do not cover.

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?

Four sentences, each earning its place: purpose, return payload details, filtering options, and mark_read/alternative access. Information is front-loaded and there is no redundancy or fluff.

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 tool with no output schema, the description explains return content (source, citation_uri, raw payload), filtering, the side effect of mark_read, and alternate access via URL. All parameters are documented in the schema, and annotations cover safety. The description is complete for effective use.

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 descriptions cover 100% of parameters, so baseline is 3. The description adds semantic value by giving a concrete example for type ('sec_8k'), explaining that since uses ISO timestamps, and clarifying mark_read's effect on subsequent calls. It does not over-explain what the schema already covers.

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 opens with a specific verb and resource: 'Pull fired events from your subscription feed.' It clearly distinguishes this tool from siblings by focusing on alerts/events from the persisted feed, with details about return payloads and filtering that set it apart from generic list or change tools.

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 implies usage context (polling for recent alerts, filtering by type/time) but does not explicitly state when to use this tool versus alternatives like list_subscriptions or recent_changes. It provides an alternative URL for scripts/dashboards, but no direct when/when-not guidance relative to sibling tools.

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