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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds critical behavioral context beyond annotations: the summary graph drops configs, so reconstructing a write from it risks data loss. It also clarifies the output distinction between summary and complete graph, which is not captured by annotations or output schema (none exists).

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 three sentences, each earning its place: core behavior, optional-parameter semantics, and a safety warning. The most important information (what the tool returns) is front-loaded, and the warning is placed at the end where it reinforces the read-only nature. No fluff or redundancy.

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?

With no output schema, the description must convey what the tool returns, and it does: metadata plus a graph summary (node ids, types, labels) by default, or the complete graph (nodes with positions/configs and all edges) when includeGraph is set. It also gives the necessary warning about graph reconstruction. For a read-only retrieval tool with two parameters, the description is complete enough for an agent to call it correctly and safely.

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 describes includeGraph as 'Return the full nodes/edges graph instead of the summary. Required reading before an update_pipeline.' The tool description reinforces and expands this by explaining that the complete graph includes 'every node with position and config, and every edge' and that the summary includes only node ids, types, labels. It does not add meaning for pipelineId beyond the name and required status, but with schema coverage at 50% the description compensates well for the includeGraph parameter.

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 'Get one pipeline: metadata plus a summary of its node graph (node ids, types, labels)', which states a specific verb, resource, and scope. It also distinguishes from list_pipelines (plural vs singular) and from update_pipeline (read vs write) by naming the complete-graph variant. This makes the tool's role unambiguous even before consulting the 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?

The description provides explicit guidance: 'Pass includeGraph to get the complete graph — every node with position and config, and every edge — which is what update_pipeline needs as a starting point.' It also warns against a common misuse: 'Never write a graph reconstructed from the summary: it drops configs.' This tells the agent exactly when to set includeGraph and what to avoid, going far beyond a generic 'use this when you need a pipeline'.

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