Agent Experience (AX)

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

The description goes well beyond the readOnlyHint annotation by explicitly stating that it 'leaves the target repository unchanged' and disclosing a real side effect: it 'uses a per-user external cache.' It also adds determinism and composition guarantees, which are important behavioral traits not visible in the schema or annotations. There is no contradiction: the cache note qualifies the read-only guarantee.

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?

Every sentence earns its place: the first defines the metric in plain terms, the second explains composition and determinism, the third states the return payload, and the fourth discloses side effects and safety. The core purpose is front-loaded)Skip, and the language is dense without being padded.

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?

Because there is no output schema, the description compensates by specifying the return shape at a useful level: 'sub-scores, drivers, and concrete recommendations for raising AX,' plus the markdown option. It could go slightly further on cache behavior or failure semantics, but for a deterministic read-only scoring tool with a fully documented input schema, this is reasonably 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?

Schema description coverage is 100%, so the schema already documents all four parameters. The description does not add significant new meaning about parameter formats or edge cases; it only reinforces the spirit of the query parameter by describing the change request as 'how cheap and safe is it for an agent to make this change here?' This meets the baseline but does not exceed it.

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 a specific verb and resource: 'Score Agent Experience (AX): a single 0–100 number.' It then defines what AX measures (cheapness/safety of a change) and lists its four components, making the tool's purpose unmistakable and clearly distinct from the raw engines it composes, such as change_impact.

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 gives clear context for when to use this tool: when an agent needs an aggregate AX score and concrete recommendations rather than raw engine output. It states that the tool is 'composed from the change_impact, token-estimate, and CODEOWNERS engines — no new analysis,' which implicitly positions it as the higher-level or synthetic choice among sibling tools, though it does not explicitly list exclusions.

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