seed_decrees

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does disclose the authorization requirement (founder-only), the idempotent nature ('if not already present'), and implies a write operation by 'Seed'. This covers the most critical behavioral traits. However, it doesn't describe the outcome — what happens when decrees are already present, whether the operation is a bulk atomic insert, or what the response looks like — leaving some behavioral uncertainty.

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?

Two sentences with no wasted prose, and the most safety-critical constraint ('FOUNDER ONLY') is front-loaded ahead of everything else. The parenthetical enumerating the decrees is dense but informative. It earns a 4 rather than 5 because the long list of internal jargon terms (fossil-grounded, embodiment-enforced) adds comprehension load without immediate operational value.

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 single-parameter tool with no output schema and no annotations, the description is reasonably complete: it covers the action, the target content, the authorization gate, and the conditional nature of execution. The remaining gaps — exact return value and explicit behavior when decrees already exist — are minor for a simple seeding operation and do not impede correct invocation.

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 0%, so the description must compensate for the undocumented founder_key parameter. It does add meaning by explaining that the founder key is what authorizes the operation ('Requires the founder key'), tying the parameter to the 'FOUNDER ONLY' constraint. This is useful, but it doesn't clarify the expected format, source, or validation semantics of the key, which is a modest gap given the single-parameter surface.

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 states a specific verb ('Seed') and resource ('the standing decrees'), with a scoping condition ('if not already present'). It enumerates the decrees being seeded (Senthar runtime, governance-is-code, etc.), giving the agent a concrete sense of what will be created. It falls just short of a 5 because it doesn't explicitly differentiate itself from siblings like add_decree or list_decrees, and the parenthetical list is jargon-heavy that assumes prior context.

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 communicates a strong precondition — 'FOUNDER ONLY' and 'Requires the founder key' — which tells the agent when it is authorized to call the tool. However, it gives no guidance on when to use this tool versus near-siblings such as add_decree or govern, and it never states when not to use it. The 'if not already present' line hints at idempotent usage but doesn't frame a decision rule between alternatives.

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