scf_trigger_window_assessment

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

Discloses it is a write operation requiring editor+ role, is asynchronous, and returns 422 when prerequisites are missing. Annotations only provide readOnlyHint=false and destructiveHint=false, so the description adds meaningful behavioral context without contradicting them.

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?

Single sentence packs operation, scope, role, async behavior, and error condition with no filler. Key differentiator ('windowed', 'one portfolio') is front-loaded.

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?

Covers role, async behavior, prerequisite error, and scope; the input schema fills parameter details. It does not state the successful return payload (likely a queued assessment ID), but sibling get/list tools partially cover the follow-up, so this is a minor gap.

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 100% and parameter descriptions already supply source (org_id from scf_list_organizations), prerequisites (evidence_id frequency tracking), and default for assessment_source. The tool description adds portfolio context but does not change parameter interpretation.

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?

Description names a specific operation ('Queue'), a distinct resource type ('windowed AI assessment'), and defines its scope ('scores every file in the evidence item's frequency window as one portfolio'). This differentiates it from sibling single-file triggers such as scf_trigger_evidence_assessment and from retrieval tools like 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?

It states the conditions that must hold ('tracking or frequency must exist', evidence_id parameter references scf_update_evidence prerequisite) and notes async execution. It does not explicitly name alternative tools or say when not to use it, but 'windowed' and 'as one portfolio' imply the selection criterion.

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