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

Annotations already declare readOnlyHint=true and destructiveHint=false; the description confirms this with 'Read-only: nothing is recorded' and adds substantial beyond-annotation behavior: the exact signing protocol (Ed25519 over ASCII bytes, base64url), the signature format `<protected_header>..<signature>`, and the fields that must be passed through verbatim. No contradiction with annotations.

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?

Four sentences with zero filler, and the highest-value facts come first: audience, then return values, then signing steps, then the read-only guarantee. Every sentence carries a distinct piece of the calling protocol.

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 bears the full burden of explaining return values, and it names all three outputs plus the exact downstream complete_task parameters. Minor gaps — where worker_kid originates and the precise JSON shape of the returned object — keep it from a perfect score.

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 only 40% (task_id and summary have prose; outcome has only an enum; acting_worker_id and evidence_artifact_ids have none), yet the description adds no per-parameter guidance and never mentions acting_worker_id or evidence_artifact_ids at all. The workflow context implies that task_id/outcome/summary feed the payload, but with low coverage the burden to compensate was higher than what this description delivers.

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 (prepare) and resource (a signable completion payload), and is immediately concrete: it returns the JCS-canonicalized payload, JWS protected header, and signing input. The workflow framing around complete_task distinguishes preparation from the actual submission step, so an agent can tell the two apart.

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?

Opens with an explicit audience constraint ('Attested workers only (you hold your own Ed25519 private key)') and closes with an explicit exclusion: 'Delegated workers do not need this — Tango signs for them.' It also routes the follow-up step to complete_task with exact field names, so when to use it versus the alternative path is fully specified.

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