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

Annotations already establish readOnly/destructive/openWorld, and the description goes further by disclosing the 25-conversation batch cap, per-conversation language handling, and the critical non-persistence behavior. It stops short of cost/latency expectations for an AI generation call, which would matter for batching decisions.

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?

One compact paragraph, front-loaded with the core verb and the batch limit, then the two modes, then the persistence caveat. No sentence is filler.

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 no output schema, the description carries the return-value burden and does state that only summaries are returned and nothing is stored. It does not say precisely how summaries map back to convoIds (array vs keyed object), which is the one thing an agent still has to guess.

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 the key semantic that agentId/convoIds and items are alternative input modes with transcripts auto-loaded for the former. The mode enum is left entirely to the schema, which already documents 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+resource+output artifact ('Generate one-paragraph AI summaries for up to 25 conversations, in each conversation language'). It also disambiguates from the collection/inspection siblings by declaring it does not persist anything, routing persistence to update_conversation.

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 presents the two invocation forms ('Simple form: agentId + convoIds...' vs 'Advanced: items [{convoId, transcript}] with your own text') so the agent knows which path to take, and names update_conversation as the alternative when the summary must be saved.

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