unified_search

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 does so well by disclosing the three retrieval arms (BM25 with Chinese bigram handling, KG fanout for wf_/commit/uuid IDs, exact ID-prefix/title match) and the RRF fusion constant k=60, which tells an agent how results are ranked and why short ID queries behave differently. It stops short of stating auth requirements, latency, or result-limit failure modes beyond what the schema covers.

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?

Four sentences, each earning its place: scope first, ranking mechanics second, use case third, exclusion last. The technical RRF detail is dense but directly actionable rather than padding.

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 an output schema present, return values need not be explained. The description covers scope, ranking behavior, query forms, and the sibling alternative, leaving nothing an agent needs in order to call it 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%, so the baseline is 3; the description adds meaning by explaining that the query can be free text or an OS ID and that ID-shaped inputs (wf_/commit/uuid) trigger a knowledge-graph fanout, which is behavior the schema does not convey. Limit and project_id semantics remain schema-only, which is acceptable given the coverage.

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 (search) and scope (all OS knowledge: task memos, reports, tasks), and explicitly distinguishes itself from the sibling memory_search by excluding direction-layer memories. An agent can tell what this retrieves without opening the schema.

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 names the use case ('recall past work, by a free-text question or by an ID') and states the exclusion with the alternative: 'Direction-layer memories are not indexed here; use memory_search.' This is the when-to-use / when-not-to-use pattern at full strength.

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