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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that the set is hashed before checking, weights are untrusted metadata, output is quarantined, and nothing is verified. This is substantial transparency. It stops short of describing side effects like immutability or the durable anchor's implications, which would push it to 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 description is four sentences, but each carries essential information: what to submit, the weight warning, return values, and the rationale for hashing before verification. It is front-loaded with the core purpose and avoids redundancy, making it appropriately concise for the complexity.

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?

Despite no output schema, the description explains the return values (candidate_set_id, commitment hash, per-candidate ids) and the quarantine state. It covers the essential context for an agent to understand the full lifecycle of this commit step, including the cryptographic commitment and the 'cannot be selectively disclosed' property. This is sufficient for a tool of this 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 100%, providing baseline 3. The description adds value by clarifying the semantics of proposal_weight ('never confidence and never ranks anything') and emphasizing that the candidates array must contain EVERY raw candidate. This goes beyond the schema's basic descriptions, earning a 4.

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 specific action: 'commit a COMPLETE raw candidate set BEFORE any evaluation.' It identifies the resource (raw candidate set), the verb (commit), and distinguishes itself as step 1 in a pipeline, separate from evaluation. This differentiates it from siblings like candidate_get or candidate_narrow.

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 phrase 'Candidate Engine step 1' and 'BEFORE any evaluation' clearly indicate when to use this tool. It also emphasizes supplying the query, generator, method, and every raw candidate. However, it does not explicitly mention alternatives or exclusionary conditions, such as 'do not use after evaluation,' so it lacks a fully explicit when-not-to-use clause.

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