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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely non-structured behavior: ordering (most recent first), an enforced result cap, and the 'truncated' flag to detect clipping. Only lacking is what happens past the cap (no offset/cursor mentioned).

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?

Three tight sentences with no waste: purpose and scope first, then filter, then paging caveat. Every clause earns its place.

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?

Output schema exists so return shape needn't be restated, and the description covers paging/truncation, which the schema wouldn't. Minor gap: it doesn't say how to retrieve results beyond the cap, and model_id's source/origin is unstated.

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 0%, so the description must carry the load and largely does: it documents the limit bounds (default 20, max 100 — the max is not in the schema at all) and enumerates status values. model_id is only implied via 'one target model' rather than explicitly named/explained.

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?

Specific verb + resource ('List assessment runs') plus scope ('for one target model') and an explicit ordering ('most recent first'). This distinguishes it cleanly from siblings like get_assessment_status (single status) and list_findings (findings, not runs).

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?

States the scoping requirement (one target model) and the optional status filter with its allowed values, which gives clear context for when to use it. It stops short of naming alternatives (e.g., use get_assessment_status for a single run's progress) or stating exclusions.

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