spend_decide

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

With no annotations, the description carries the full burden of behavioral disclosure. It fully discloses the return format (allow/block + Ed25519-signed receipt), provenance content (weights origin, jurisdiction, retention), privacy stance (content-free, never prompt content), fail-closed behavior for unknown self-hosted models, and how optional identifiers are bound into the signed actor. This is far richer than the typical 'updates settings' description.

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?

Five sentences, each earning its place: purpose, metadata constraint, return value/provenance, prerequisite, and identifier semantics. The main action is front-loaded ('Gate a model call BEFORE it runs'), and there is no filler or repetition.

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 7 parameters and no output schema, so the description must cover return values and edge behavior. It explains the allow/block decision, the signed receipt with provenance, fail-closed behavior, and identifier restrictions. It does not describe every error path, but for a gating tool the core context an agent needs to call it correctly is present.

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 100%, so the baseline is 3. The description adds meaningful semantics: it classifies model, token counts, and endpoint_url as metadata, warns never to pass prompt content, restricts agent_id/task_id/workflow_id to identifiers, and clarifies that unrecognized endpoint_urls route as self-hosted. This goes beyond the schema's per-parameter descriptions, though it doesn't exhaustively elaborate every field.

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: 'Gate a model call BEFORE it runs.' This clearly states what the tool does and distinguishes it from siblings like spend_status (status reporting), export_receipts (exporting), and verify_receipt (verification). The return value (allow/block plus a signed receipt) further pins down its unique role.

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 explicitly states when to use this tool ('before a model call runs'), what to pass ('metadata only... never prompt content'), and names a prerequisite alternative: 'Unknown self-hosted models need set_model_cost first (fail-closed).' It also clarifies that read-only and cost-configuration tools accept the optional fields without recording a spend decision, giving agents a clear decision boundary.

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