claim_native_dispatches

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the description's added value is the note that it 'is the real native bridge; it never runs codex exec as a fallback' — a genuinely useful behavioral disclosure about what happens on failure. However, it omits the lease/mutation semantics entirely: what a claim commits, whether it expires, and what happens on retry are all unstated.

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?

Three short sentences with no filler, and the core action is front-loaded. The procedural instruction and the bridge disclaimer each earn their place, though the phrasing 'this is the real native bridge' is slightly defensive rather than informative.

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 mutating claim operation with a lease parameter, no output schema, and zero schema documentation, the description leaves critical gaps: what a successful claim returns, what happens when the lease expires, and whether claims can be released or re-claimed. An agent could call it, but not confidently reason about the lease lifecycle.

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% for three parameters, so the description carries the full burden and fails to explain any of them. host_id, limit (batch size 1-12), and especially lease_seconds (15-3600, i.e. how long the claim holds) are all left to the agent to guess from bare names and bounds.

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 opens with a specific verb and resource ('Claim queued Codex-native tickets') and scopes it to 'this current host', so the core action is unambiguous. It stops short of naming a sibling such as delegate_task or retry_fallback to distinguish when this beats them, so it lands at 4 rather than 5.

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?

It prescribes a follow-up sequence ('for every ticket, call spawn_agent, then native_subagent_started'), which is useful procedural guidance. But it never says when to use this tool versus delegate_task or delegate_batch, nor what preconditions (host registration, queue state) must hold, leaving the selection decision to inference.

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