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

Annotations already establish readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds useful behavior (recency, newest-first order), but no detail on limits, pagination, or what data each run includes.

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?

One compact sentence with no filler; the verb and core scope are front-loaded, and the ordering behavior is appended efficiently.

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 read-only list operation with rich annotations and a minimal two-parameter schema, the description covers action, resource, and ordering. It does not specify return shape or limit default, but these are not critical 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%, so the description must compensate for both parameters. It implies pipelineId through 'for a pipeline' but never names it or the optional limit parameter, nor explains default or constraint semantics.

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 uses a specific verb ('List') and resource ('recent runs for a pipeline') and adds the ordering behavior ('newest first'). This clearly distinguishes it from sibling tools like get_run (single run) and run_pipeline (create/execute).

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 'for a pipeline, newest first' gives a clear context for when to call the tool, but it does not explicitly name alternatives or exclusions such as using get_run for a single run. It stops short of the explicit routing seen in the highest tier.

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