fingerprint_feature

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

No annotations are provided, so the description carries the full burden, yet it never states that this is a read-only, deterministic lookup, what the fingerprint format is, or what happens if the version ID is unknown. Worse, the appended upgrade pitch ('Requires Kiln Pro', pricing URL) is promotional payload that conveys no behavior and may be misread as gating the tool itself.

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 one useful sentence is front-loaded, but roughly two-thirds of the text is marketing copy about calibration, mid-print edits, textures, a Pro tier, and a pricing URL—none of which helps an agent invoke this tool. Substantial waste in a short definition.

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?

With no annotations, no output schema, and an undocumented parameter, the description should explain what a content-addressed fingerprint is, what it enables (integrity checks, release signing), and how it relates to verify_feature_release/sign_feature_release. Instead it leaves those gaps and fills the space with an upsell.

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% for the single parameter, so the description must compensate, and it barely does—it only implies the ID refers to a feature version. It says nothing about where feature_version_id comes from (e.g., list_feature_versions) or whether it accepts a version label versus an opaque 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 first sentence gives a specific verb + resource: 'Return the content-addressed fingerprint of a feature version.' That is decisive and distinguishable from most siblings, though it never contrasts with the closely related fingerprint_model or the release-verification tools. The remainder of the text is unrelated to the purpose and dilutes it.

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?

There is no guidance on when to call this versus fingerprint_model, verify_feature_release, or sign_feature_release. The only secondary content is a paywall notice ('Requires Kiln Pro'), which reads as an access restriction rather than a usage condition and could wrongly discourage an agent from calling the tool at all.

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