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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered structurally. The description adds real value by disclosing the merge behavior: steps are preserved unless remove_step_ids names them, clarifying that the tool is not destructive by default despite the destructive annotation. It could go further (e.g., how top-level fields like title or sender merge on update), but the preservation disclosure is meaningful beyond the annotations.

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 zero filler. The core create/update purpose and component list are front-loaded in the first sentence, and the critical preservation behavior occupies the second. Every clause earns its place, with the highest-risk semantic detail placed last.

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 complex tool (12 params, deep nesting, output schema present), the description is minimal but the schema carries the heavy lifting at 100% coverage and the output schema explains returns. The essential agent-facing knowledge — create vs. update and the non-destructive-by-default step semantics — is present. A small gap remains around merge behavior for top-level fields, but this is largely covered by the rich schema and annotations.

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 100%, so all 12 parameters are documented in the schema and the baseline is 3. The description adds marginal meaning by mapping 'steps, emails, waits and routing rules' to the steps structure and explicitly tying remove_step_ids to the preservation rule, but it does not explain parameter semantics beyond what the schema already provides.

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 pair ('Create or update') with a clear resource ('Chasync funnel') and enumerates the managed components (steps, emails, waits, routing rules). It plainly distinguishes itself from siblings like archive_funnel, get_funnel, and list_funnels by establishing this is the create/update entry point, so an agent can pick it 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?

The description implies usage context (creating or updating a funnel) and adds one key semantic rule — 'Existing steps are preserved unless remove_step_ids explicitly names them' — which is genuinely useful for deciding how to invoke it. However, it never explicitly contrasts with alternatives (e.g., use save_email_template for standalone templates, get_funnel to read) and gives no when-not-to-use guidance, leaving routing to inference.

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