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

With no annotations, the description must carry the full behavioral burden. It discloses only a tier ('Team') and an internal HTTP path (POST /audit), and says nothing about whether the operation is read-only, what it mutates, what happens on failure, or what permissions are needed. 'POST' hints at a write but the description does not confirm it.

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?

It is a single short sentence with no filler, so it is concise. But the parenthetical '(Team tier, POST /audit)' is arguably noise for an agent caller while the essential information is absent — brevity here reflects under-specification rather than efficiency.

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?

Three undocumented required parameters, no output schema, no annotations, and no explanation of return values or error behavior. For a non-trivial resume/audit operation this description is nowhere near sufficient to call the tool correctly.

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% and there are three required parameters (run_id, checkpoint_ns, journal), yet the description never mentions any of them. The untyped 'journal' parameter is especially opaque — no shape, format, or constraints are given anywhere.

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?

It identifies the resource ('journal-completeness audit') and the trigger condition ('for a killed run'), which is more than a restatement of the name. But the actual operation is vague — it never says whether it validates, reports, or returns a verdict — and it does not distinguish this from sibling resume_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?

The phrase 'for a killed run' implies a precondition, but there is no explicit when-to-use guidance and no mention of the sibling tools that handle adjacent resume steps (execute_effect, pin_discovery, record_effect, verdict). An agent has to guess whether to call this before or after those.

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