Build a GTM plan from the audit

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

Goes well beyond the readOnly/openWorld annotations by explaining how the plan is grounded in `sources` marked yours/competitor/third_party, that competitor sources are never placement targets, and the fallback to report issues/stats when no citations exist. Also discloses subscription requirements and free-trial details, which materially affect whether the agent should call get_sample_audit.

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 front-loaded with the core purpose, then organizes trigger phrases, behavioral grounding, parameters, and subscription constraint into distinct clauses. Although longer than minimal examples, every sentence carries load-bearing information; the subscription/trial detail is critical for correct agent routing.

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 description covers grounding, fallback, parameters, and subscription, but never states the precondition that an audit must already exist for the domain. It does not tell the agent to call run_audit first if no audit is present, which is a notable gap given the audit-dependent nature of the tool and the absence of an output schema.

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%, but the description adds meaning by explaining that `focus` and `constraints` steer the plan and that `prior_plan` holds markdown from an earlier call to refine rather than restart. This meaningfully supplements the schema's terse property descriptions.

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 action ('Build a written go-to-market plan') on a specific resource (the website's latest audit), grounded in citation evidence. Trigger phrases like 'turn this audit into a plan' and the mention of get_sample_audit clearly differentiate it from sibling tools.

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?

Provides explicit when-to-use trigger phrases ('what should I do about my AI visibility,' 'turn this audit into a plan') and a conditional alternative: if the user lacks a subscription, call get_sample_audit first. It also names the subscription prerequisite. It does not explicitly contrast with get_recommendations, which could be triggered by similar phrasing, so a small routing gap remains.

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