firestarter_market_drops

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

Annotations declare readOnlyHint=true and destructiveHint=false, and the description's 'Read-only' statement reinforces rather than contradicts them. The description adds genuine context beyond the annotations: the full return payload (id, discount, claimed vs cap, status), the full status enum with the pending_seller_approval edge case spelled out, and the integration note that the drop id feeds firestarter_cancel_drop. Deducting one point because the basic read-only guarantee is already carried by annotations, so the description's marginal contribution, while good, is not exceptional.

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?

Packs a complete mental model — ownership scope, return fields, status semantics, cancel flow, usage triggers, and sibling distinction — into ~150 words with no padding. Front-loads the most critical differentiator (OWN) and keeps the alternative-tool handoff to a single compact sentence at the end. Withholds a perfect score only because 'Read-only' and the phrase 'a drop on another seller's listing' restate, respectively, what the annotations and earlier clauses already establish.

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 simple read-only filter tool with one parameter and no output schema, the description is exhaustive: it covers the return shape, all possible status values including the edge case, the cross-tool id contract, example queries, and the sibling-vs-owner boundary. There is no output schema to compensate for, and the description leaves nothing material unexplained for an agent to invoke this tool correctly.

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% — the single program_id parameter is already documented as 'The market/program id you own (from firestarter_my_markets).' The description echoes and enriches this by centering the ownership constraint ('on a market you OWN') and explaining what the returned data looks like (claimed vs cap, status, listing, tier gate, expiry), which helps an agent reason about the parameter without re-stating its syntax. Baseline 3 at full coverage, and the description earns one extra point by clarifying ownership semantics that the param schema names 'market/program' — a noun the description resolves.

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?

Specifies a clear verb+resource ('List the community-sponsored drops on a market you OWN') with an explicit parenthetical tying it to firestarter_create_drop. It distinguishes itself from its sibling firestarter_drops ('This is the OWNER view; buyers discover... with firestarter_drops'), leaving no ambiguity about which of the two drop-related read tools applies.

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 triggering conditions with natural-language quotes: "'how are my drops doing?', 'how many people claimed my drop?', or wants to see what drops are still live before creating another." It also names the exact alternate tool (firestarter_drops) to use instead when the user is a buyer, and references firestarter_cancel_drop for the id handoff, giving the agent a full decision tree for routing.

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