Get Own Marketplace

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds genuinely non-obvious behavior: no automatic refresh or polling, the required API key, the sign-in-then-token flow, and specific 401/403/429 recovery steps. It loses a point because a large block of mutation-flavored errors (409 reconciliation, 422 atomicity, full-Inbox pending) reads as copy-paste from a write tool and can make a read-only GET look stateful.

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?

Purpose, side effects and returns are reasonably front-loaded, but the Errors block dominates the text with boilerplate irrelevant to a 2-parameter read (conflict reconciliation, operation IDs, 422 atomicity, inbox capacity). On a read-only idempotent tool this padding dilutes the sentences that actually earn their 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?

With no output schema, the explicit 'Returns: {state, serverTime}' is valuable, and auth, side effects and failure modes are all covered, which is more than enough for a simple read. It falls short of 5 only because the error section is generic rather than tailored, leaving the shape of 'state' still undefined.

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% and both parameters are documented in-schema, so the baseline applies. The description does add one useful cross-field constraint — the sessionToken must be the accessToken returned by a sign-in, and userId must be the user who signed in (reinforced by the 403 guidance) — but it adds nothing else about format or scoping.

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 verb ('Reads') and resource ('marketplace') are stated, but the object is left vague: 'current own marketplace state or configured limits' never says what 'state' contains, and the 'or configured limits' clause overlaps confusingly with the sibling horizon_get_marketplace_limits. An agent must open the schema/docs to know whether this returns balance, listings, or limits — and may pick the wrong sibling.

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?

It has explicit 'Use when', 'Not for' and named-alternative structure, and it redirects to horizon_get_marketplace_operation for reconciliation, plus concrete prerequisites (sign in via horizon_signin_email/anonymous, pass accessToken as sessionToken). The 'Use when' clause is weak and mismatched though ('explicit marketplace actions' describes a write, not a read), so the routing value is partly undermined.

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