slua_search_reference

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds two genuine behavioral traits beyond that: ranking is deterministic (results are stable across calls) and pagination is bounded. It stops short of saying whether matching is substring, whole-word, or case-sensitive, which is the most important behavioral detail for a "literal word search" tool.

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?

A single well-formed sentence with no filler, and the differentiating detail ("literal word search") is front-loaded. Its brevity is efficient rather than padded, though the space saved is spent nowhere useful given the undocumented parameters.

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?

An output schema exists and rich annotations are present, so the description needn't explain return shape or safety. Still, for a four-parameter search tool with zero schema documentation, the agent is left without the meaning of `kind`, the matching semantics of `query`, or any routing rule against the twelve sibling lookup/search tools.

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 all four parameters, so the description carries the full burden and largely drops it. The `kind` filter (function/event/constant/type) is a meaningful narrowing dimension that is never explained, and nothing clarifies that `query` is matched word-wise rather than as a substring, or how `limit`/`offset` interact for paging.

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 description names the mechanism ("literal word search") which usefully distinguishes it from a semantic/fuzzy search, and the tool name supplies the resource (reference docs). However, it never states which corpus is searched (SLua reference) and never distinguishes itself from the near-identical sibling lsl_search_reference or from slua_lookup_symbol, so the agent must infer the scope from the name prefix alone.

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?

There is no when-to-use guidance at all — nothing says whether to prefer this over slua_lookup_symbol for exact symbol names, or over lsl_search_reference for the other dialect. The word "literal" hints that it will not handle conceptual queries, but that is inference rather than stated guidance.

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