Baseline Create

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

Annotations declare destructiveHint=true)Skip to content, but the description does not disclose that creating a baseline may be a write/destructive operation (e.g., writing a sidecar file, potentially overwriting existing). It mentions 'write the git-diffable baseline sidecar there' but does not clarify if it modifies the registry or requires special permissions. With destructiveHint not being readOnly, the description should explicitly state side effects. The description does not contradict annotations (it says write, which aligns with destructive), but it fails to carry the burden of behavioral disclosure.

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 well-structured, with an initial summary sentence followed by a paragraph on fingerprinting and then parameter explanations. It is front-loaded with the core purpose. However, it includes extra context (issue #142, C3) which may be unnecessary for tool invocation, slightly reducing conciseness. Overall, it's efficient and readable.

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?

Given that the tool has 6 parameterscars with complex semantics, the description covers each parameter and the return value ('Returns the baseline object'). It also mentions determinism. However, it doesn't explain error conditions or how the 'out' path interacts with the registry, but this is minor. With no output schema, the description's mention of the return object is valuable. Overall, it is quite 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 0%, so the description must compensate. It does: it explains 'label' as the baseline label, 'registry' as path to items.json sidecar, 'items' as optional subset of item ids, 'base_dir' as artifact root, 'note' as optional description, and 'out' as optional path for writing the baseline. This adds meaning beyond the schema, which only has titles and defaults. The description gives clear semantics for each parameter, so it's strong.

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 it creates a labeled, immutable baseline snapshot with version/fingerprint semantics. It distinguishes itself from sibling 'baseline_verify' by explicitly mentioning 'for reproducible rebuilds' and referencing issue #142, C3. The purpose is specific and unambiguous.

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 implies when to use it (for reproducible rebuilds, pinning artifact bytes) but does not explicitly state when not to use it or compare to alternatives like 'baseline_verify'. It provides context on the registry and fingerprinting but lacks explicit exclusions. Since there is a sibling 'baseline_verify', some guidance would help, but the context is sufficient.

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