loop_start

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

Adds real value beyond the annotations by clarifying that this is a state-writing operation that records verify_argv but never executes shell commands — a non-obvious behavior given the 'verify-until-done' framing. Annotations cover idempotency and non-destructiveness, but the description usefully reinforces the write-only, no-execution contract.

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?

Two tight sentences, front-loaded with the core action and immediately followed by the behavioral caveat that matters most. No filler or redundancy.

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 an 8-parameter state-writing tool with annotations but no output schema, the description covers the key surprise (no shell execution) and the create-or-resume duality. It does not describe what the call returns or how authority/auth works, but the schema's authority_file entry covers the latter.

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 88%, so the schema already documents all eight parameters including verify_argv's 'recorded, never run' semantics and name's repo+name resume behavior. The description restates the verify_argv point rather than adding new meaning; baseline 3 is appropriate.

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 and resource: 'create or resume a durable verify-until-done loop contract.' An agent can distinguish this from loop_status, loop_record_attempt, and loop_stop by the 'create or resume' framing, though no sibling is named explicitly.

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 implies usage ('create or resume' a loop contract) but gives no explicit when-to-use or when-not-to-use guidance, and never points to alternatives such as loop_status for inspection or loop_stop for teardown. The resume condition (same repo+name) lives only in the schema, not the description.

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