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

The description details mark_read behavior that modifies state (flags events as read), which contradicts the idempotentHint annotation indicating the tool is idempotent. This is a critical inconsistency.

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 main purpose, each sentence adds distinct value. No fluff or repetition.

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?

Covers return fields, filtering, mark_read semantics, and alternative access. Lacks explicit pagination details but is sufficient for basic 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?

Though schema covers all parameters, the description adds practical context: examples of type filter ('sec_8k'), ISO timestamp format for since, and the effect of mark_read/unread_only. It also notes default limit of 50 and alternative feed URL.

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 the subscription feed, specifying the returned data (source, citation_uri, raw payload). It distinguishes itself from sibling tools, none of which perform this function.

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?

Provides guidance on filtering by type and since, notes the mark_read option for reading state, and mentions alternative access via HTTP. However, it does not explicitly contrast with 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.