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

Annotations provide readOnlyHint=false and destructiveHint=false. The description adds key behavioral traits: the submission is reviewed by a person and nothing goes live automatically. However, it does not explain the callback_url mechanism, idempotency behavior (despite external_ref hinting at it), or what happens after submission. Some transparency is provided, but gaps remain.

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 four sentences, tightly packed with meaningful information: purpose, freeness, review process, ethical guidelines. No filler. Front-loaded with the core action. Every sentence earns its place.

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 15 parameters, no output schema, and a callback mechanism, the description lacks important context. It does not explain the response format, the callback flow, or the external_ref idempotency feature. While the human review note is useful, the tool's full workflow is not conveyed, leaving an agent underinformed.

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 low (40%). The description adds generic semantics for relationship and contact parameters (e.g., 'Say honestly whether you own the business' and 'Never invent contact details'), but does not detail each of the 15 parameters or explain optional fields like callback_url or external_ref beyond what the schema already describes. The contribution is marginal.

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 states 'Submit a business to NUM' with a specific verb and resource. It distinguishes from sibling tools like num_search_places and num_list_submissions by focusing on submission for review. The additional context of free/unmetered and human review reinforces its unique role.

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 ethical usage guidance (e.g., 'Say honestly whether you own the business' and 'Never invent contact details') but does not explicitly compare to sibling tools like num_submit_promo or state when not to use this tool. The guidance is helpful but lacks direct alternatives or exclusions.

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