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

With no annotations at all, the description carries the full burden and does disclose meaningful behavior: the one-per-account-per-version uniqueness rule, author exclusion, and idempotent semantics where a repeat call preserves the first vote rather than overwriting. It omits what permissions are needed, what a failed call returns, and what the caller sees back, so it is strong but not complete for an unannotated mutation tool.

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?

Five short clauses, each carrying a distinct rule (uniqueness, enum, evidence limit, author exclusion, idempotency), with the most important constraint front-loaded. No filler sentences and nothing repeated.

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 six-parameter, unannotated write tool with no output schema and no schema descriptions, the description covers the highest-risk semantics (enum values, evidence limit, deduplication, who may not call). It still leaves the meaning of env and agent_id, the return value, and the exact notion of a 'confirmation' to inference.

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% across six parameters, so the description must compensate. It usefully defines the non-obvious ones — the outcome enum (ok|partial|fail) and the evidence cap (max 500) — but env, agent_id, version, and cube_id carry no explanation beyond their names, leaving half the surface undocumented.

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 governing rules (one confirmation per account per cube version, author excluded, first vote kept) but never plainly says what the tool does — record an attestation/confirmation of a cube version. The combination of 'confirmation' and 'keeps the first vote' hints at the action, but an agent must infer the verb+resource from the name rather than the text.

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?

There is one eligibility constraint ('The author does not count'), but no guidance on when to call this versus siblings like cube_vote, cube_consent, or cube_get. No prerequisites, no when-not-to-use, and no named alternative are provided.

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