Recall Conversations

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so safety is covered. The description adds valuable behavioral detail beyond annotations by specifying the return format: recent conversation summaries newest-first, each with a short summary, key topics, decisions, open action items, and timing. This is useful context even though a few edge cases like empty results are not mentioned.

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 front-loaded with the core purpose frosted by illustrative examples and a clear return-value breakdown. It could be slightly tighter—the list of sample phrases and the 'ALWAYS call' reminder are a little redundant—but every sentence contributes to the agent's decision-making, so it remains efficient and well-structured.

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?

Given only 2 optional parameters and rich annotations, this description is complete. It covers the tool's purpose, when to invoke it, what output to expect, and how it differs from a related sibling. Since there is no output schema, the description's explicit enumeration of returned elements compensates well, leaving no critical gap for an agent to call the tool correctly.

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 description coverage is 100%, and both 'limit' and 'query' are already well described in the input schema. The description does mention that the tool returns 'recent' summaries, which loosely aligns with 'limit', but it adds no meaningful extra semantics beyond what the schema provides. Baseline 3 is appropriate.

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 recalls past conversations across earlier sessions, including voice and video calls, and explicitly contrasts itself with read_company_wiki. It names the specific resource ('past conversations') and the action ('Recall'), making it easy for an agent to distinguish from siblings like read_wiki or search_documents.

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?

The description gives explicit trigger phrases ('what were we talking about last time?', 'where did we leave off?') and instructs the agent to 'ALWAYS call this before saying you don't remember'. It also provides a clear alternative boundary by stating it is distinct from read_company_wiki, which covers curated durable facts rather than past chat back-and-forth.

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