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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses the key behavior that this is a proposal, not an authoritative command, and clarifies the credit cost and authority model. It does not specify side effects like persistence or notifications, but the core behavioral trait is clearly stated. The output schema helps cover return values, so the description does not need to explain those.

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 three sentences long, front-loaded with the primary purpose, and each sentence adds valuable information: purpose, who decides, and the authority/cost model. No word is wasted.

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 8 parameters, 2 required, nested objects, and no schema descriptions. While the output schema exists, the description does not provide enough context for an agent to know how to construct a valid request, especially fields like assertion and evidence. It gives only a high-level overview, leaving significant gaps in operational understanding.

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 compensate for the 8 parameters. It mentions 'boundaries, policies, or context flags' which loosely maps to constraint_type values but omits 'relationship'. It does not explain other critical parameters like assertion, evidence, severity, confidence, or discovery_context. The agent would lack sufficient guidance on how to fill these fields correctly.

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 ('Propose') with a clear resource ('organisational constraint') and explicitly states the purpose ('for human review'). It distinguishes from sibling tools like declare_constraint by emphasizing that humans decide whether to promote, making the tool's unique role unmistakable.

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 clearly indicates when to use this tool: when agents discover boundaries, policies, or context flags that require human decision. It also explains the authority gate ('humans decide whether to promote') and the low barrier (1 credit), implying that this is for non-authoritative suggestions. However, it does not explicitly name alternative tools (e.g., declare_constraint) for promotion, but the context is strongly implied.

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