rtfm_search

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

With no annotations, the description carries the full disclosure burden. It reveals a key behavioral trait: results contain no content, only source paths and line ranges. It also indicates ranking behavior. This goes beyond the tool name and helps set expectations, though it omits details like defaults or side-effect disclaimers.

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?

Two dense sentences with zero filler. The action is front-loaded, the return format is stated, and the companion tool is cited. Every word earns its place.

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 search tool with a fully specified input schema, the description covers the essential output behavior and points to the natural next step. It doesn't need to explain return values beyond what it states, and remaining gaps like default result count are minor and handled by the schema.

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 the baseline applies. The description adds no parameter-level meaning beyond the schema's own descriptions; all parameters are already documented adequately in the input schema.

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 and resource ('Search the indexed knowledge base') and explicitly specifies the output shape ('ranked source paths with line ranges, no content'). It distinguishes itself from rtfm_expand by noting that content reading is handled there, making the tool's role unmistakable.

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 a clear directive: use rtfm_search to get ranked locations and rtfm_expand to read content. This is a concrete when-to-use/alternative pairing. It does not enumerate other sibling tools, but the search-versus-read distinction is sufficient for most routing decisions.

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