mcp_pipeline

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

Beyond the generic annotations (readOnlyHint=false, openWorldHint=true, etc.), the description discloses critical behavioral details: interpolation via {{step_id.path}}, step skipping via 'if' path checks, the default abort on error with continue_on_error option, max 20 steps, and no recursion. It also describes the return structure. This goes far beyond what annotations convey.

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 well-structured with bold section headers: Purpose, When to use, When NOT to use, Step shape, Example, Returns, Limits. It front-loads the purpose and uses concise bullet-like phrasing. Every section adds necessary information, and the example is compact yet illustrative. No fluff or repetition.

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 complex meta-tool with only one top-level parameter (steps), the description covers purpose, usage criteria, step schema, interpolation, control flow (if/continue_on_error), return format, and operational limits. The presence of an output schema reduces the need to detail return values, but the description still summarizes them. It is fully complete for an agent to decide when and how to invoke it.

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?

The schema already has 100% coverage with descriptions for all properties, including default id naming. The description adds a concrete example showing interpolation and step chaining, plus clarifies 'if' path semantics ('resolves to falsy') and that args support placeholders. This adds meaningful context beyond the schema, though the schema already does substantial work, so a 4 is appropriate rather than a 5.

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 clear, specific statement: 'Execute a sequence of MCP tool calls in one request.' It further clarifies the unique interpolation capability, which distinguishes this orchestration tool from all sibling tools that perform single operations. This is a specific verb+resource definition that leaves no ambiguity about what the tool does.

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 explicitly states when to use ('when a workflow needs ≥2 sequential calls'), when NOT to use ('parallel-safe independent calls', 'long-running batch ops'), and points to an explicit alternative ('dedicated bulk tool (Plan 7+)'). This is exemplary usage guidance covering both inclusion and exclusion criteria.

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