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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world. The description goes beyond that by specifying the output shape (ak.provenance.v1, RFC 9162 inclusion proof against the signed tree head, trust checks, keys URL), which is valuable context not in the annotations. However, since there's no output schema, this relies on prose to convey return structure, which it does adequately.

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?

Front-loaded with the output first, then usage, then exclusions, then input/output. Every clause earns its place; no redundancy.

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?

Since there's no output schema, the description helpfully names the return format and key fields. Covers input formats and behavioral expectations. Minor gap: doesn't state what happens if the proof fails or if the capability is unknown, but overall complete for a read-only retrieval tool.

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 coverage is 100%, so the schema already fully documents the single 'capability' parameter including accepted formats. The description repeats this ('a capability id, ak:// URI or slug') without adding syntax or validation details beyond the schema. Baseline 3 is correct.

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?

States a specific verb+resource (retrieves provenance for one capability) and enumerates what it returns: artifact hash, manifest hash, signed publisher and registry attestations, and a transparency-log inclusion proof. Distinguishes itself from siblings by explicitly ruling out get_benchmark and get_capability.

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?

Has explicit 'Use when' (verifying a package matches what the registry published and signed) and 'Not for' clauses naming the alternative tools get_benchmark and get_capability. Nothing is left to inference.

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