tool_guide

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: it discloses the two real failure modes it targets (wrong document kind, false negative on capability), warns that an empty result is not evidence of absence, explains that `task` is keyword-matched, and names the returned keys (`recipes` with `use`/`avoid`/`note`, `not_possible`, `matched`).

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 critical instruction is front-loaded and the rest is organized by concern. It loses a little to self-referential meta-commentary about how `tool_catalog` matches this description and how the word 'help' used to miss it — useful for maintainers, but it consumes space without telling the calling agent anything actionable.

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 three-optional-param advisory tool with no annotations and an output schema present, everything an agent needs is covered: when to call, when not to trust an empty result, what the three params accept, and what comes back. No material gap remains.

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% (params have only titles and empty defaults), so the description must compensate and does: `task` is free-form natural language matched on keywords with a worked example, `document_kind` enumerates library/board/schematic/project/any, and `backend` enumerates altium/kicad/easyeda with the meaning of omitting it.

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 definition states a specific role — a troubleshooting/recipes lookup that answers what the right tool and prerequisites are, what the sibling tool you probably wanted is, and what is provably impossible. It also explicitly separates itself from `tool_catalog` (which resolves missing tool names), so an agent can choose correctly without opening either schema.

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?

It gives an explicit trigger ('USE THIS BEFORE CONCLUDING A CAPABILITY IS MISSING') plus a concrete enumeration of situations: tool seems missing, unsure which tool to use, operation seems unsupported, or a call failed on the wrong document. It also names the fallback (`tool_catalog`) and the condition under which an empty result does not mean impossibility.

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