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

With no annotations, the description fully discloses behavior: it re-downloads every file, scales with total locker bytes, returns match=True/False, and requires payer authorization via signed envelopes. It also details the action_required='sign_envelopes' response for keyless deployments, going well beyond a simple read-only label.

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 dense but efficiently organized: the first sentence defines the core operation, the second covers cost and comparison, and the third handles authorization. Every sentence adds essential context without unnecessary filler.

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?

For a complex tool with no annotations, the description covers purpose, usage conditions, cost, authorization flow, and key return outcomes. It leverages the output schema for detailed return structure while mentioning the critical match=True/False cases. The only minor omission is receipt_id semantics, but overall it is complete for the tool's complexity.

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 0%, so the description must compensate. It explains the envelope parameter thoroughly, especially in the keyless deployment flow ('re-call with envelope=<signed result>'), but does not explain receipt_id. With two parameters and one unexplored, the description leaves a notable semantic gap.

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 clearly states the tool's function as a byte-level integrity proof: it re-downloads files, recomputes hashes, rebuilds the Merkle tree, and compares against the persisted attestation. It also explicitly distinguishes itself from nukez_verify by noting it is slower and for different use cases.

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?

The description provides explicit guidance: 'Slower than nukez_verify — reach for this only on audits, post-migration sanity checks, or when you suspect drift' and 'For routine integrity checks, nukez_verify is the right tool.' It also explains the authorization flow for signer-mode vs keyless deployments, which directly informs when each approach is relevant.

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