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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the read-only nature is known. The description adds valuable context about the response structure (ordered stages and semantic types open/won/lost), which is beyond the annotations and helps set expectations.

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 a single sentence that front-loads the primary action ('Read one pipeline') and includes essential details without redundancy. 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 simple get tool with one parameter and no output schema, the description covers the purpose, identifier type, and key return elements. It does not mention potential error cases or the exact format of 'key', but given the low complexity and rich annotations, it is sufficiently complete.

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 input schema only defines 'pipeline' as a string with no description. The description clarifies that this parameter can be a 'key' or 'pl_id', adding meaning beyond the schema. The 0% schema coverage is compensated by this explanation, though examples or format details are absent.

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 clearly states the tool reads one pipeline by key or pl_id, and lists what is returned (ordered stages with semantic types). This distinguishes it from sibling tools like relm_list_pipelines (listing multiple) and relm_manage_pipeline (mutating).

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 'Read one pipeline' implies use for single pipeline retrieval, contrasting with listing tools, but there is no explicit when-to-use or alternative guidance. The context suggests it competes with generic relm_get, but no exclusion is given.

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