scf_bulk_assess_windows

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses that this is a write operation requiring editor+ role, that it is async, and that items lacking tracking or a frequency set appear under `skipped_detail`. This meaningfully explains side effects and edge-case behavior, though it does not detail post-queue tracking or partial failure semantics.

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 with no filler; the core operation is front-loaded, and the parenthetical captures role and async behavior efficiently. The skipped-item behavior is placed where it is actionable.

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 2-parameter async queue operation, the description covers inputs, role requirement, async behavior, and a key response field (`skipped_detail`). It does not mention how to check the outcome of the queued assessments, but sibling tools exist for that and no output schema is expected.

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 100%, so the baseline is 3. The description adds the skipped_detail behavior tied to evidence_ids, but does not add new syntax, format, or selection guidance beyond what the input schema already documents.

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 uses a specific verb ('Queue') and resource ('windowed AI assessments'), and scopes the operation to 'up to 25 evidence IDs.' This clearly distinguishes it from the single-item trigger/list/get siblings like scf_trigger_window_assessment and scf_get_window_assessment.

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 description implies batch usage with 'up to 25 evidence IDs' and notes the async write nature, but it does not explicitly state when to prefer this over scf_bulk_assess_evidence or scf_trigger_window_assessment. No exclusions or alternative routing are provided, so the agent has to infer the intended use case.

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