research.recall_chain

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

No annotations are provided, so the description carries the full behavioral burden. It implies a read-only search over stored reasoning but says nothing about scope (all chains vs. current session), how many results are returned by default, ranking behavior, or what a result contains. For a recall tool with zero annotation coverage this is a meaningful gap.

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?

Two short sentences, front-loaded with the core action before the illustrative example. No filler. Slightly under-specified rather than verbose, but structurally sound.

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, no annotations, and one undocumented parameter, the description should say more about what a recalled chain looks like and how results are bounded. It conveys the retrieval intent adequately but leaves the agent guessing about return shape and scope.

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 50%: the schema already documents 'query' with its own example, while 'limit' is entirely undocumented in both schema and description. The description's 'by topic' framing duplicates rather than extends the schema, and the accidental-looking overlap between the schema's 'Orama vs Elasticsearch' example and the description's question adds no new meaning.

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: 'Search past research chains by topic.' Clearly a read/lookup operation, which implicitly separates it from the research.start_chain / add_step / conclude write-side siblings. It stops short of naming sibling alternatives like research.archaeology, so an agent must infer the distinction.

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 worked example ('why did we choose Orama?') gives a concrete scenario, which is useful implied guidance for retrieval-style questions. However, it never states when to prefer this over research.archaeology, memory.recall, or research.deep_compare, nor any preconditions for chains existing.

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