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

Annotations already indicate readOnly, idempotent, non-destructive. The description adds critical behavioral context: mark_read mutates read state (despite readOnlyHint), polling is suitable, and the feed is also accessible via a direct URL. This supplements the annotations without contradicting them.

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 (4 sentences) and front-loaded with the core action. Every sentence adds essential information: what returns, what it contains, how to filter, how mark_read works, and the alternative HTTP access. No wasted words.

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?

The description covers the return structure (source, citation_uri, raw payload), filtering, mark_read, polling, and alternative access. Given no output schema, it provides sufficient context. Minor omission: it doesn't mention pagination or limit behavior explicitly, but the schema covers limit.

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%, but the description adds meaningful value beyond the schema: it explains the purpose of each filter (type, since), the effect of mark_read on subsequent calls, and the unread_only option. It does not simply repeat schema names.

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 'pull fired events from your subscription feed' and specifies that it returns alerts with source, citation_uri, and raw payload. It distinguishes itself by explicitly mentioning filtering options and the mark_read behavior, and there are no sibling alert tools to cause confusion.

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 good usage guidance: it explains how mark_read works for polling, mentions that the same feed is available via HTTP for scripts/dashboards, and describes filtering by type and since. However, it does not explicitly compare this tool to other sibling tools or state 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.