search_capture

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

With no annotations, the description carries the full burden and does so unusually well: it discloses that hybrid may return BM25 results marked 'pending' while an index job continues, that semantic indexing is bounded by per-capture byte and token budgets, and that oversized captures fall back to immediate BM25. It omits permission/auth requirements, but the latency, fallback, and pending-state semantics are exactly the kind of hidden behavior an agent needs.

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?

Purpose is front-loaded in sentence one, followed by behavioral caveats and then a clean Args list; nothing is wasted in a structural sense. The budget/wait prose is somewhat dense and partially repetitive (budget behavior is explained twice), which keeps it from a 5.

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?

Complexity here is high, but the description covers the ranking modes, the default prefetch, timeout and fallback behavior, and all five parameters; an output schema exists so return values needn't be explained. An agent could call this correctly from the description alone, with only auth/permission context missing.

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% across 5 parameters, so the description must compensate, and it largely does: it names every parameter, gives query examples, spells out the three mode values with their meanings, and adds the 'must be non-negative' constraint on context_lines. top_k and capture_id are only restated from the schema defaults, leaving marginal room to improve.

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 first sentence gives a specific verb (Searches) and resource (captured command output) plus the ranking mechanisms (BM25, Semantic, Hybrid/RRF), which lets an agent separate this from retrieval siblings like get_capture_slice or get_capture_summary. It stops short of naming those siblings to draw the boundary explicitly.

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 makes the mode trade-off explicit ('hybrid' is recommended, 'bm25' for keyword terms, 'semantic' for vector concepts) and states the semantic prefetch default, so mode selection is well-supported. It does not state when *not* to use this tool or how it compares to the other capture-reading tools, so it falls short of a full 5.

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