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

Annotations declare readOnlyHint=false, destructiveHint=false and openWorldHint=false; the description adds the missing context an agent needs — it is free, needs no key, and returns allowed/reason/tier/next-step fields (valuable since there is no output schema). The one friction point is tension with the schema: it claims 'no key and no registration' while an api_key parameter exists and query=register is itself a registration, which could confuse an agent deciding whether credentials are needed.

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 critical disambiguation is front-loaded in five words and every clause carries information (action list, returned fields, register shortcut, alternative tool, cost/auth). The middle sentence is a long dash-chained run-on that is slightly harder to parse than necessary.

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 5-parameter, nested-object tool with no output schema, the description supplies the return shape, the auth/cost posture, the registration path and the sibling alternative. It does not explain when api_key/agent_id become relevant or what structured_payload is for, which are the remaining gaps.

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 goes further by framing requested_action as a reputation-gated access decision and by mapping query=register to the marketplace_register flow. It leaves api_key, agent_id and structured_payload entirely to the schema, which is acceptable given the full coverage.

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?

Opens with an explicit disambiguation ('Not a conversation: a typed access check for a program') and names the concrete verb/resource: pass a requested_action and receive an allow/deny verdict with tier and next steps. An agent can immediately distinguish this from the chat-style sibling contact_sphere and from marketplace_register.

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?

States when not to use it ('To ask something and get an answer, use contact_sphere') and gives the alternative route for registration ('query=register registers you through the same door as marketplace_register'). Both the exclusion and the substitution path are explicit, leaving nothing to inference.

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