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

Annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds context about the feed persistence, the effect of `mark_read` on subsequent calls, and the data returned (source, citation_uri, raw event). This goes beyond what annotations provide.

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 three sentences, each earning its place: purpose, return details, filtering and mark_read usage, and polling guidance. No redundancy, clear front-loading.

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 lacking an output schema, the description explains what the tool returns (source, citation_uri, raw payload). All parameters are covered, usage guidance is given, and behavioral aspects (feed persistence, mark_read effect) are disclosed. The tool is simple, and the description is 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, the baseline is 3. The description adds practical meaning: it gives an example for `type` ('sec_8k'), explains `since` as ISO timestamp, and clarifies that `mark_read` flags events as read so next calls show only newer events. This is useful beyond the schema's minimal 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 starts with a specific verb-resource pair ('Pull fired events from your subscription feed') and clearly distinguishes the tool from siblings like 'list_subscriptions' and 'subscribe'. It states exactly what the tool returns (source, citation_uri, raw payload).

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 notes that polling works fine and provides an alternative access method via a GET endpoint, which guides when to use this tool vs. manual fetching. However, it doesn't explicitly mention when not to use it, though the read-only nature is clear from annotations.

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