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

With no annotations present the description carries the full burden, and it does substantial work: it names the exact artifact set produced, discloses that pending events are rolled into a final block first (a side effect), explains the offline verification path and key location, documents the summary's tier grades and coverage ratio, and spells out authorization semantics (Bearer holder_secret, 401/403, frozen pre-holder-auth AITs). It does not state idempotency, rate limits, or whether repeated generation alters the chain further, which keeps it from a 5.

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 purpose and artifact list are front-loaded, and most sentences carry real information (contents, offline verification, grading semantics, auth failures). The dated '**Holder authentication (2026-10-16).**' heading reads like changelog residue and the paragraph runs long, but the density of useful detail keeps waste low.

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?

There is no output schema, so the description must describe returns, and it does: the ZIP contents, the summary's grading scheme, and the anchored-bid coverage ratio. Combined with explicit authentication and failure-mode behavior, an agent has enough to call it correctly. The remaining gap is the unexplained input parameters, which is the one dimension left unaddressed.

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% and there are two parameters, one of which is an enum ('full' vs 'summary'). The description never explains what the 'ait' identifier is, its format, or what the 'format' enum toggles — the mention of a tier-graded summary.json is about output contents, not the full/summary input switch. With the schema silent and the description not compensating, the agent must guess at the parameter contract.

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 states a precise verb+resource combination — assembling the ATAP v0.1 §7.5 Receipt ZIP for an AIT — and even enumerates the archive contents (manifest.json, AIT, attestation chain, witness key, summary.json, verify.sh). That is far more specific than a generic receipt tool. It stops short of 5 because it never explicitly contrasts itself with sibling receipt tools like generate_receipt, get_receipt, or verify_receipt, leaving the agent to infer the ATAP/AIT context as the differentiator.

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?

Useful context is implied: an AIT must exist, its block chain must be writable, and holder authentication is required (401/403 behavior, frozen legacy AITs must be re-registered). That effectively describes when this call will succeed versus fail. However, it never says when to pick this tool over generate_receipt or verify_receipt, and there are no explicit exclusions, so usage remains inferred rather than guided.

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