query

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

With no annotations provided, the description carries the full burden and does so well: it declares read-only behavior ('nothing is sent to anyone'), explains that `scope` boosts ranking rather than filtering, and states that it returns rows rather than an answer. It omits anything about result limits, pagination, or index freshness.

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?

Three tight sentences, front-loaded with the verb and corpus, then the non-obvious scope semantics, then the safety and sibling routing. Nothing is padded or repeated.

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 two-parameter read tool with no annotations and no output schema, the description covers purpose, the counterintuitive ranking behavior, the row-level return shape, the read-only guarantee, and the alternative tool. An agent has everything needed 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 both parameters are already documented. The description's note that scope boosts ranking rather than filtering largely restates the schema's own wording, so it adds little beyond the structured field despite being accurate.

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) over a specific corpus (decisions, changes, answered questions) for a natural-language question. It also distinguishes itself from the sibling `ask`, which handles the case where the ledger has no answer.

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 routes the agent to `ask` when no answer exists in the ledger and a teammate should respond, which is a real when-not rule. It gives no guidance relative to the other overlapping retrieval siblings (`check_decisions`, `decisions`), leaving that differentiation implicit.

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