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

Annotations declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds: it returns most recent alerts, explains the effect of mark_read (flags returned events read so next call shows newer ones), mentions unread_only option, and confirms polling works. No contradictions.

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, front-loaded with core purpose and immediate details. Every sentence adds value: first states purpose, second lists return fields, third explains filters and mark_read, fourth mentions polling and alternative endpoint.

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 5 parameters and no output schema, the description fully explains return values and behaviors (mark_read, unread_only, polling). It covers expected input format and provides an alternative access method. No gaps.

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 description adds meaning: type example 'sec_8k', since as ISO timestamp, mark_read explains flagging behavior, limit range (1-200, default 50), unread_only returned events read_at null. All parameters are enriched.

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 'Pull fired events from your subscription feed' and specifies the returned content (source, citation_uri, raw payload). It distinguishes from the numerous sibling tools which have distinct purposes.

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 when to use filters (type, since) and the mark_read/unread_only options. It also mentions that polling works fine and points to an alternative feed for scripts/dashboards. Lacks explicit when-not-to-use guidance, but context is clear.

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