rag_pipeline_plan

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the agent knows this is a deterministic pure-computation call. The description adds moderate context beyond that: the plan surfaces 'open questions' and deliberately stops short of vendor selection, which tells the agent not to expect a concrete product recommendation. It says nothing about depth, determinism guarantees, or how assumptions are handled.

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 front-loaded sentence with zero filler; the resource and its coverage areas come first, and the scope caveat lands last where it belongs.

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 output schema covers return values, so the description needn't explain them, and annotations cover the safety profile. However, for a tool requiring five structured inputs including a nested corpus object with enums, the total absence of parameter semantics leaves the definition under-specified for correct invocation.

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 5 required params plus a nested corpus object with 5 sub-fields, so the description carries the full explanatory burden and largely fails. 'Authorization' maps to one parameter, but useCase, latencyBudgetMs, citationsRequired, and every corpus sub-field (documents, averagePages, formats, updateFrequency, languages) go entirely unexplained — no guidance on how they change the output.

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?

Specific verb + resource: 'Plan a retrieval-augmented generation pipeline', and it enumerates the exact facets the plan covers (chunking, embedding, indexing, authorization, evaluation, cost drivers). The RAG-specific framing plus 'No vendor is chosen for you' distinguishes it from the generic planners in the sibling list such as implementation_plan or architecture_pattern.

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 phrase 'from corpus facts' implies prerequisite inputs and 'No vendor is chosen for you' rules out vendor selection, so usage is implied. But there is no explicit when-to-use vs. when-not guidance and no routing to alternatives such as implementation_plan or architecture_pattern for follow-on work.

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