generate_conversation_summaries

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

Adds real context beyond the annotations: the 'does not store' side-effect clarification, the 25-item cap, the transcript auto-loading, and the per-conversation-language output. It does not mention cost, latency, or what happens on an invalid convoId or >25 items, and the non-idempotent AI-generation behavior implied by idempotentHint=false isn't spelled out.

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, each doing distinct work: capability, simple path, advanced path, plus the storage caveat. The most important constraint (non-persistence) is placed last but is short enough not to be buried.

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?

No output schema exists, and the description covers the key contract ('Returns the summaries only'), but does not indicate the response shape (e.g. array keyed by convoId, ordering, or how failures for individual ids surface). For a batch AI-job tool that is a small but real gap; everything else an agent needs to invoke it correctly is present.

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 75% and the description still adds meaning: it pairs agentId with convoIds as one mode and explains that items carry 'your own text' instead of auto-loaded transcripts, which clarifies the otherwise ambiguous two mutually exclusive param groups. The mode enum is already fully documented in the schema, so the description doesn't repeat it.

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 and resource ('Generate one-paragraph AI summaries for up to 25 conversations, in each conversation language') and immediately distinguishes itself from the mutating siblings by noting the output is not persisted. The batch limit and per-conversation-language output are concrete and differentiating.

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 separates the two invocation paths ('Simple form: agentId + convoIds' vs 'Advanced: items [...] with your own text') and names the follow-up tool for persistence ('use update_conversation to save one'). It stops short of saying when to prefer this over simply calling get_conversation and summarizing elsewhere, but the alternative routing is largely handled.

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