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

With no annotations, the description carries the full burden. It usefully discloses the auth requirement (subscriber token) and account scoping, but says nothing about whether invoking it mutates run state, whether it is idempotent or safe to retry, or what a 'verdict' contains — critical for a tool sitting next to execute_effect and record_effect.

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?

One sentence with no filler, so nothing is wasteful, but the dense parenthetical is cryptic rather than front-loading the essential information. Brevity here reflects under-specification, not disciplined economy.

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 five-parameter, four-required tool in a checkpoint/resume workflow with no annotations and no output schema, the description is far too thin. The auth and scoping kernels are helpful, but the agent still lacks enough context to call it confidently or understand the return contract.

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 five parameters, so the description must compensate and largely does not. 'Checkpointed run' only loosely gestures at run_id and checkpoint_ns; node, declared_effects, and current_discovery_digest get no explanation at all.

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 names a concrete artifact (a signed resume verdict) for a checkpointed run, which is more specific than a tautology. However, 'verdict' and 'resume' are domain jargon with no explanation, and nothing distinguishes this from siblings like resume_execute_effect or resume_record_effect beyond the noun 'verdict'.

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 notes a subscriber-token prerequisite and points at POST /verdict for equivalent semantics, but never states when to call this versus the other resume_* tools. An agent has no exclusions, no ordering guidance, and no indication of what preconditions the checkpointed run must satisfy.

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