scf_assessment_write

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

Annotations already declare readOnlyHint=false and destructiveHint=false; the description adds the editor+ role requirement and the async/queued nature, which the annotations do not cover. It omits the more consequential behaviors — that rejecting a window raises deficiencies, that verdict decisions are version-bound, that bulk calls cap at 50/25 — leaving those to the schema. Notably, 'rejected raises a deficiency per in-scope control' is a side effect sitting under destructiveHint=false, but that disclosure exists in the schema rather than contradicting the description text.

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?

A single front-loaded sentence that compresses eight dispatch methods into parallel clauses ('assess a file or many, assess a window or many'), with no wasted words and the permission/async qualifier placed high.

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 15-parameter polymorphic dispatcher with no output schema, the description is thin: it never states that exactly one method must be chosen and that required parameters vary by method, nor what each method returns (counts, skipped_detail, poll targets). The schema carries most of that load, so the definition is workable, but the top-level description does not fully prepare an agent for method dispatch.

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 the enum descriptions already tag each parameter with its applicable method ('Used by: ...'), including prerequisites and 422 conditions. The description contributes no parameter semantics beyond that, so the baseline 3 applies.

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 and resource ('Run and review AI evidence assessments') and enumerates the eight concrete operations (assess file/window, bulk, refresh stale, confirm/override verdicts, set acceptance). The '(write)' title and the tool name separate it from scf_assessment_read, though the description never names that read sibling as the alternative, so the differentiation is inferred rather than stated.

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?

'(editor+, async)' tells the agent the required role and that operations are queued rather than synchronous, which is real selection context. However, no when-to-use guidance appears in the description itself — the per-method routing (which method to pick, what to poll afterward, when to skip) lives entirely in the schema's enum descriptions, so the description alone only implies usage.

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