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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description goes beyond them with genuinely useful behavior: it never calls the model, never bills, and returns a null summary when no cache exists — non-obvious traits that affect how an agent should interpret the result.

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?

Three short sentences, no waste, and the read-only guarantee and null-cache case are surfaced up front where an agent will see them before deciding to call.

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?

With an output schema present, return-value detail is unnecessary, and the description still covers the one edge case that matters (null when uncached) plus the read-only cost profile. Nothing needed to invoke this correctly is missing.

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?

Only one parameter and schema description coverage is 100%, so the schema carries the semantics. The description refers to 'a conversation' but adds no format or constraint detail beyond the schema's own conversationId entry. Baseline 3 applies.

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?

States a specific verb (Read) and resource (cached AI summary of a conversation) plus the freshness qualifier, and it is clearly distinguishable from get_conversation_messages and refresh_conversation_summary. An agent knows exactly what it gets without opening the schema.

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?

Explicitly routes regeneration to refresh_conversation_summary, which is the key alternative an agent would consider. It doesn't state when to prefer this over reading raw messages via get_conversation_messages, so it stops short of full when/when-not coverage.

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