Build a context packet

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

The description implies a read-only summarization behavior and lists what the packet includes. The readOnlyHint annotation already covers side effects, so no contradiction exists and the added output details support transparency.

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?

The description is two compact sentences, begins with the core action, and contains no filler or redundant wording.

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?

It explains the high-level output and use case but lacks parameter semantics and output format. Since there is no output schema and params are only partially inferable, an agent would need more details to invoke it with confidence.

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?

The schema covers all five parameters but has zero descriptions, and the description never names or explains query, budgetTokens, conversationIds, includeExternal, or maxConversations. 'Token-budgeted' and 'stored conversations' only hint at two of them.

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 uses a specific verb ('assembles') and names the deliverable ('token-budgeted brief') plus its contents (decisions, open questions, action items, excerpt, contradictions). It also positions the tool against the common alternative of pasting a transcript.

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?

It gives a concrete usage signal: use instead of pasting a whole transcript. It does not enumerate when each sibling might be preferable, but the stored-conversation summary use case is clear.

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