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

With no annotations provided, the description carries full burden and does so excellently. It discloses the fixed routing policy, deterministic moat, quarantine of unroutable claims ('held, never judged'), sealing of the full set with trace, and refusal behavior. This is rich behavioral context beyond simple narrowing.

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 concise: three sentences with no redundancy. It front-loads the purpose ('Candidate Engine step 2') and immediately explains the process, then adds critical refusal and input instructions. Every sentence contributes meaning.

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?

This is a complex tool with a nested parameter and no output schema, but the description covers the input requirements, process, and constraints thoroughly. It hints at the output via 'sealed with its ordered trace' but does not explicitly state the return value or next step, which would be a minor addition for complete guidance.

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?

The schema provides a description for cset ('the committed set, verbatim from candidate_commit'), giving high coverage. The tool description adds semantics like 'exactly as candidate_commit returned it' and 'COMMITTED set', reinforcing the constraint that the input must be unaltered and committed, which is not fully captured by the schema structure alone.

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 the tool 'narrows a COMMITTED set' as step 2 of the Candidate Engine, which is a specific verb+resource. It clearly distinguishes from candidate_commit (step 1) and candidate_get by describing the narrowing process, fixed routing policy, and sealing of the full set.

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 identifies the tool as step 2 and instructs to pass the set exactly as candidate_commit returned it, implying sequential use after commit. It also states it refuses uncommitted or altered sets, providing a when-not condition. However, it does not explicitly name alternatives beyond the implied predecessor.

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