List Assertions

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

With no annotations, the description carries the full burden, and it delivers: it discloses that inherited assertions are included, that the three verdict fields are independent, that coherence_status 'pending' does NOT block verification, and that passing tiers does not mean the control verifies. It also explains the meaning of origin, covers, tier1_attested, and evidence_provenance. This is rich behavioral context beyond the schema.

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?

The description is long but every section earns its place: the one-of constraint, the origin field, the three verdict fields with their caveats, and the pointer to get_sufficiency. It is front-loaded with the core purpose and the most critical usage rule. Slightly verbose in the verdict-field section, but the warnings are important enough to justify the length.

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?

The tool has an output schema, so return values are already structured, but the description still explains the semantics of the non-obvious fields (origin, tier1_status, tier2_status, coherence_status, covers, tier1_attested, evidence_provenance). It also covers the key pitfall (per-control verification) and routes to the right sibling. For a list tool with this complexity, nothing essential is missing.

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 75%, and the description adds the critical constraint that exactly one of control_id or assumption_id must be provided, which the schema only hints at via 'omit if using...'. It also clarifies the semantics of the returned fields, which helps the agent interpret results. It doesn't document server_version or model_id, but those are self-explanatory and the schema covers them.

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 opens with a specific verb and resource: 'List active assertions for a control or assumption.' It immediately distinguishes the tool's scope (active assertions, flat list) and names the two valid target types. It also differentiates from siblings like get_sufficiency and get_verification_report by explicitly saying verification is decided per control and should be read from get_sufficiency, not inferred here.

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 gives an explicit selection rule: 'Provide exactly one of control_id or assumption_id.' It also tells the agent when NOT to use this tool for a verdict: 'never infer it from the tier fields here' and directs to get_sufficiency. This is clear routing guidance relative to siblings.

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