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

Annotations only say not read-only and not destructive; for a 14-parameter mutation that creates or forks builds and can carry a plan/routes/variants, the description discloses nothing about side effects, idempotency semantics, or what 'preserve requested sales-funnel steps' actually constrains. 'Read authoring guidance' hints at an external prerequisite but never says which guidance or what happens if it is skipped.

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 two short clauses with no padding, which is good, but it is terse to the point of being cryptic rather than front-loaded with useful information. 'Read authoring guidance' consumes roughly a third of the text without conveying an actionable referent.

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?

This is a deeply nested schema (plan -> routes -> checkout -> variants -> rules), 14 parameters, required idempotency_key, and no output schema, yet the description supplies none of the behavioral or parameter context needed to invoke it correctly. For this complexity level the definition is essentially inadequate.

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 only 7% across 14 parameters, so the description carries the burden and fails: mode, plan, brief, build_id, source_build_id, page_ids, wait_seconds, and idempotency_key all go unexplained. It hints at three mode values but omits edit_pages and says nothing about how plan/routes/sections or the fork source IDs are used.

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?

It names a resource (builds) and several mode verbs (new/resume/fork), so an agent can roughly tell what it does versus builds_list/builds_get. But it omits the 'edit_pages' mode that the schema exposes, and 'Open a build' in the annotation title reads differently from the description's create/resume/fork framing, leaving the actual operation ambiguous.

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?

'Read authoring guidance' is an instruction with no pointer, handle, or prerequisite stated, so the agent has no actionable routing. No sibling is named (e.g. builds_save, builds_validate, checkout_plan_edit) and no condition distinguishes when to open a new build versus resume, fork, or edit pages.

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