search_help

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

With no annotations, the description carries the behavioral burden, and it does so well: it discloses that all query words must match, that scope is a corpus named after the install archive, that the search is version-exact, and that results are result paths usable with get_help_page. It doesn't explicitly confirm non-mutating behavior or describe result ordering/pagination, but 'search' plus the local-documentation framing makes this largely transparent.

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?

The description is longer than average but well-structured: purpose first, usage guidance second, follow-up chain, then an Args section. Most sentences earn their place, especially the scope parameter explanation. It is slightly expansive in enumerating manual categories, but that reinforces the tool's breadth without becoming filler.

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?

The tool has no output schema, yet the description compensates by indicating what a result yields ('a result path') and how to continue with get_help_page. It also explains the scope model and when to invoke the tool. Missing explicit return-format details and pagination are minor gaps for a search tool that is otherwise well contextualized.

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 coverage is 0%, so the description must compensate, and it does. 'query' is explained as search words that all must match, 'scope' is given a meaningful corpus model with named examples, and 'limit' is described as max results. This adds real semantic value beyond the bare schema, though scope could have been more exhaustive about valid archive names.

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 opens with a specific verb-resource pair: 'Search the running Houdini's own documentation' and enumerates the covered domains (VEX, expressions, HOM, effects manuals). It is clearly distinct from sibling get_help_page by framing itself as a search step and explicitly directing follow-up to get_help_page.

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 gives explicit when-to-use guidance: 'Use this BEFORE improvising' and lists concrete scenarios like unsure workflows, VEX/expression functions, or Solaris/TOPs concepts. It names get_help_page as a follow-up, but does not explicitly state when NOT to use this tool or how it compares to get_workflow_guide, so it stops short of a 5.

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