kernel_extensions_receipt

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

With no annotations at all, the description still carries meaningful behavioral content: it identifies the cryptographic guarantee (kernel's Ed25519 signature) and a conditional output variation (a download watermark appears when fetched from a watermarking marketplace provider) — a non-obvious trait an agent could not get from the schema. It omits error behavior when no receipt exists and never states the operation is read-only, leaving real gaps for a zero-annotation tool.

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?

One sentence, front-loaded with the core action before the supporting detail; nothing is redundant. The em-dash construction and the trailing watermark clause load a lot into a single sentence, which slightly reduces scannability but stays economical.

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 no annotations, no output schema, and an undocumented parameter, the description does a fair job sketching return content (who/when/where, signature, watermark). However, it leaves out the failure mode when no receipt exists, the meaning of 'id', and any note that this is a safe read — all of which an agent needs given no structured fields cover them.

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 required parameter 'id', and the description only weakly disambiguates it by saying the receipt is 'for an extension'. It does not state whether 'id' is the extension identifier, name, or bundle id, nor any format constraint, so it does not compensate for the empty schema.

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?

Specific verb plus resource: 'Get the install receipt for an extension', immediately qualified by what the receipt proves (who, when, where, Ed25519 signature). This is unmistakably distinct from sibling operations like kernel_extensions_list, install_bundle, or uninstall, which manage extensions rather than report provenance.

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?

Usage is implied by the framing around provenance/audit ('proves WHO installed it WHEN and from WHERE'), but there is no explicit when-to-use guidance, no statement of prerequisites (e.g. must the extension already be installed), and no named alternative or exclusion. The agent must infer the audit scenario.

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