aiworkhub_manager_skill_evidence_sweep

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

No annotations are present, so the description carries the burden and does so well: it discloses the write nature (MANAGER WRITE), idempotency (a second sweep records nothing new and activates nothing twice), resumability, and what gets reported (skipped_by_reason, activated). It does not mention required permissions, but the mutation and repeat-safety profile is clear.

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?

Front-loads the operation type and purpose, then layers in pagination, reporting, and idempotency notes. The parentheticals earn their place, though it runs slightly long for a two-parameter tool.

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?

An output schema exists, so return explanation is a bonus rather than required, yet it still names the key report fields. Combined with coverage of resumability and idempotency, the only material gap is the absence of guidance on choosing this sweep over its per-record siblings.

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 0%, so the description must compensate. It explains the cursor parameter's role for continuation, but names it "next_cursor" while the schema field is "cursor," creating a mild mismatch, and it never clarifies the limit parameter's meaning or default of 200.

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: "backfill learning-commit evidence for every recorded commit," tagged MANAGER WRITE. It sets scope (bulk sweep over every commit) that implicitly differs from per-record siblings like skill_add_evidence, though it never names an alternative 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?

Explains how to operate it (pass next_cursor to continue past a ledger larger than limit) and that re-running an unchanged window is a no-op. But it gives no guidance on when to choose this bulk sweep versus the single-record skill_add_evidence or skill_mine siblings.

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