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

Annotations already indicate destructiveHint=true and readOnlyHint=false, so the agent knows this is a mutating, destructive operation. The description adds valuable context that discarding does not change app files, clarifying the precise side-effect scope. This goes beyond what annotations convey without contradicting them.

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, efficient sentence that front-loads the core purpose and includes the key qualifier. There is no fluff or redundant wording, and every element 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 two-parameter tool with annotations covering safety profiles and the schema documenting parameters, the description provides sufficient context on what the tool does and its side-effect boundaries. It doesn't repeat return-value information (no output schema) and the missing usage guidance is already addressed in the usage dimension.

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 fully describes both parameters (app_id: 'The app ID', change_set_id: 'Change set ID'). The description adds no additional parameter-level meaning, so with 100% schema coverage the baseline score of 3 is appropriate.

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 ('discard'), identifies the resource ('pending staged change set'), and adds a clarifying qualifier ('without changing app files'). This distinguishes it clearly from sibling tools like apply_change_set and create_change_set. An agent knows exactly what action and scope this tool covers.

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 states the action ('discard a pending staged change set') but provides no explicit guidance on when to use it versus alternatives like apply_change_set or validate_change_set. It implies usage for discarding changes, but there are no explicit when-not or alternative selection cues, leaving the agent to infer the proper context.

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