Verify Audit Export

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

Annotations already declare readOnly, idempotent, non-destructive. The description adds significant context: 'No network calls', 'anything else fails closed', 'On failure, brokenAt pinpoints...', and the security recommendation about out-of-band keys. No contradiction.

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 long but information-dense; every sentence serves a purpose. It's front-loaded with the primary action and then systematically covers algorithms, security notes, failure handling, and tool compatibility. Slightly dense as a single paragraph but warranted.

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 output schema, the description takes on the burden of explaining outcomes. It describes failure output (brokenAt plus canonical codes) and key provenance, but does not explicitly describe a successful result's shape (e.g., whether it returns a boolean or summary), leaving a small gap.

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% with detailed parameter descriptions, but the tool description adds extra context beyond the schema: e.g., it explains where to fetch publicKeys (GET /v1/verification-keys) and that result.keyProvenance distinguishes key sources, which isn't in the 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?

The description opens with a specific verb and resource: 'Verify an AGLedger record audit export offline (format 2.0, COSE_Sign1).' It clearly distinguishes itself from siblings by directing the user to agledger_api for obtaining the export and to attestation for raw stream.

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?

It explicitly states when to use this tool ('For an independent audit, pass publicKeys obtained out of band') and how to obtain the input ('Obtain the export via agledger_api...'), and contrasts with alternatives (raw COSE_Sign1 stream via attestation).

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