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

Goes well beyond the annotations by disclosing what is preserved (earlier decision remains in history; stage, archive state and screening evidence untouched) and that the operation is partially applied with per-entry results. It does not cover permissions required or whether reopening can be undone by a subsequent outcome call, and the 'destructiveHint: true' framing is only implicitly reconciled.

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 tight sentences, front-loaded with scope and precondition, then preserved state, then per-item result semantics. No filler and nothing restated from the schema except the 100 cap, which is load-bearing here.

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?

With no output schema, the sentence 'read every entry in results' usefully signals a per-application results array, and the preserved-state note covers the mutation risk. But for a required batchId and an optional note with no explanation anywhere, the definition leaves real gaps an agent cannot resolve.

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 coverage is only 25% — only workspaceId is documented in the schema. The description implies candidateIds (up to 100) but never explains the required batchId or the optional note, leaving two of four parameters opaque in both structured fields and prose.

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States a specific verb (reopen) and resource (applications with a hired/rejected/withdrawn outcome) plus the batch cap of 100, so the effect is unambiguous. The terminal-outcome precondition effectively separates it from record_hiring_outcome and reject_candidate, 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?

Clearly states the applicability condition: only applications already in hired, rejected or withdrawn state. It does not name an alternative tool or spell out when-not to use it (e.g., correcting a decision via record_hiring_outcome), so it stops short of full routing guidance.

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