direct_rpc

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 explicitly discloses the write-protection mechanism (allow_write=true for mutating methods) and the generic 'call any' nature, which implies a raw passthrough with limited validation. It does not mention error behavior or return format, but for an escape hatch tool, this is a reasonable level of transparency.

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 a single, well-structured sentence that front-loads the core action ('Escape hatch: call any Direct API service.method'), then provides necessary guardrails and examples. Every phrase adds value, with no repetition or filler.

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?

Given the tool's raw RPC nature, lack of annotations, and absence of output schema, the description covers the essential aspects: purpose, write-safety requirement, example services, and guidance to prefer typed tools. It does not describe response formats or error cases, but for an escape hatch, this is not a significant gap. The description is sufficiently complete for an agent to decide whether to use it.

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 only 50% (service and method lack descriptions), so the description must compensate. It adds concrete semantics for service (listing examples like campaigns, keywords, ads) and method (listing verbs like add/update/delete/suspend/resume), and clarifies allow_write's role. The params field remains generic, but the schema's 'API params object' description and the tool's purpose give adequate context.

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 clearly identifies this tool as an 'Escape hatch' for calling any Direct API service.method with params JSON, which is a specific verb+resource combination. It also distinguishes itself from the many typed sibling tools by instructing 'Prefer typed tools,' making the purpose and differentiation explicit.

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 provides clear usage guidance by stating 'Prefer typed tools,' which tells the agent to use this tool only as a fallback. It also specifies that mutating methods require allow_write=true, giving an explicit condition for safe usage. However, it does not enumerate all scenarios when typed tools are insufficient, so it stops short of a full when/when-not comparison.

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