scf_bulk_assess_windows

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

Discloses write operation, editor+ role requirement, async execution, and that items without tracking/frequency are skipped and reported. Given no annotations, this covers key behaviors well, though could elaborate on response contents beyond skipped_detail.

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?

Two sentences, no fluff. Each sentence adds essential information: core function in first, edge-case behavior in second.

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?

Adequate for a simple input tool with full schema coverage, but lacks details about what 'windowed' means, whether a job ID is returned, or how to track progress. Could be more informative for agents unfamiliar with the domain.

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?

Both parameters have descriptive schema coverage (100%). The description adds the skipped_detail behavior but not extra parameter context. Baseline 3 is appropriate since schema already documents parameters well.

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 clearly states 'Queue windowed AI assessments for up to 25 evidence IDs' with a specific verb and resource. It mentions role and async nature, which helps differentiate from siblings like scf_bulk_assess_evidence, but does not explicitly contrast.

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?

Implies usage for windowed assessments and notes items without tracking/frequency are skipped, but does not explicitly state when to use this tool versus scf_bulk_assess_evidence or scf_trigger_window_assessment.

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