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

Annotations mark destructiveHint=true, and the description aligns while adding meaningful behavioral context: write-tier approval requirements, approval types (from-now-on vs just-once), and the instruction not to re-ask in chat after the card approves. This goes beyond what annotations alone provide.

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 compact and front-loaded: it states the core action first, then trigger examples, then approval guidance. Every sentence earns its place and avoids 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?

For a destructive tool with three fully documented parameters and no output schema, the description provides everything needed to invoke it correctly: trigger phrases, scope of effect, and approval workflow. Even without an output schema, no critical calling information is missing.

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 100%, so the schema already documents all parameters. The description adds no new parameter-level detail beyond what the input schema states, such as the effect of output_format or the source of pipeline_id.

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 begins with a specific verb and resource: 'Reset all learnings for a pipeline and start fresh.' It is clearly distinct from sibling tools like list_pipeline_learnings (read-only counterpart) and update_pipeline_style_guide (targeted update), even without naming them.

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 lists trigger phrases ('forget what you learned', 'start fresh with the style') and instructs to call it on the first clear ask. It provides clear context for when to invoke the tool, though it does not explicitly state when not to use it or name an alternative tool.

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