create_agent

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

Annotations only declare the safety profile (not read-only, not destructive, open-world, not idempotent); the description adds the consequential behavior: enableNodes is forced true, the model is pinned to claude-haiku-4-5, nodes[0].kb.enabled with maxChunks=3 / maxChunkSize=512 gets set for auto RAG, and vg_instructions will be rejected by the API. Those are non-obvious side effects and hard failure modes disclosed before invocation.

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?

Front-loaded with purpose and the sibling alternative, and nearly every clause carries a hard constraint. It is dense to the point of run-on — several distinct admonitions are packed into em-dash chains — which slightly hurts scannability for a 23-parameter tool.

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 23-parameter mutation tool with nested objects and no output schema, the description covers the high-risk configuration surfaces (prompt placement, model pinning, KB/RAG, UI Engine, lead funnel) and warns that additionalConfig rejects unknown fields. The remaining gaps — voice, theme, light mode — are fully documented in the schema, so nothing critical 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 100%, so the baseline is 3 — but the description earns above that by explaining parameter interactions the schema cannot express: systemPrompt is a mirror of nodes[0].instructions, funnelConfig is the supported path for lead alerts, vg_enableUIEngine is a master switch gating the per-element flags. It does not cover voiceConfig, light, theme, or allowRemoveTools, leaving those entirely to the schema.

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?

States a specific verb+resource ("Create a Convocore agent") and immediately qualifies it as "advanced/raw," which is the distinguishing axis against the sibling create_agent_from_template. An agent can tell which creation path it is on without opening the schema.

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?

Names the alternative explicitly ("Prefer create_agent_from_template for website/branded agents") and gives the condition that selects it. It also issues negative routing guidance — do NOT use vg_instructions, do NOT create custom HTTP webhook tools for sales alerts — which are exactly the wrong-path mistakes an agent would otherwise make.

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