search

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

With no annotations, the description carries the full behavioral burden and does reasonably well: it discloses the return shape (one-line hits with ids), the effect of context=N (adds N neighbouring turns), and the accepted time formats (ISO or 7d/12h) plus as_of and explain semantics. It omits default limits, permissions/scope, and pagination, which keeps it short of a 5.

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?

Very dense and front-loaded: the core capability leads, then output shape, then filters, in a compact semicolon-separated form with no filler sentences. The packing is slightly terse, which costs a little readability, but every clause earns its place.

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?

For a 16-parameter tool with no annotations and no output schema, the description covers the essentials: output shape is stated so no return-value schema is needed, and most filter parameters are explained. Remaining gaps (mode, limit, rerank, max_tokens, format) are minor and largely self-evident, so it is close to complete.

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 0%, so the description must compensate, and it explains roughly half the parameters with real meaning: context, project, agent_filter, tags, kinds, entity, since/until with format syntax, as_of, and explain. It leaves mode, limit, query, format, rerank and max_tokens uncovered, but the semantic additions it does provide are substantial.

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 clearly: hybrid search combining keyword, meaning, entities, time and recency, with a defined output (one-line hits with ids). It also distinguishes itself from the expand sibling by delegating detail retrieval to it. Only the generic name 'search' and the unstated corpus (implied to be turns/memory by 'neighbouring turns') keep it from a 5.

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 implies a workflow ('Returns one-line hits with ids; expand(id) for detail'), which routes the agent to the expand sibling for full detail. However, it never explicitly states when to choose this tool over others or what conditions argue against it, so usage is implied rather than prescribed.

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