market_active_rentals

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it delivers richly: 'Makes one logical GET request and does not auto-fetch continuation pages,' 'Array responses are locally limited to 100 rows and 256 KiB, with truncation reported in text and metadata,' and 'Oversized records are refused without partial fields.' It even honestly documents the broken pagination behavior of offset/skip, which is unusually candid and valuable.

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 purpose is front-loaded in the first sentence, and every sentence carries information with little filler. However, the prose is dense and slightly meandering — phrases like 'these declared selectors remain forwardable for inspection but are not working pagination' are awkward and somewhat redundant with the earlier offset/skip example. It could be tightened without losing content.

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 read tool with no output schema and 7 undocumented parameters, the description covers a great deal: scoping semantics, working vs. broken pagination, response size limits, truncation reporting (in text and metadata), and refusal behavior for oversized records. The main gap is the return value shape/format, which is not described, but given the explicit truncation and limit documentation, an agent has enough to call it reasonably.

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 0% with 7 parameters, so the description must compensate — and it does. It clarifies that owner, renter, and card_detail_id act as scoping selectors, explains that limit and take 'bound leading rows,' and flags that offset and skip are non-functional for pagination ('offset=2 and skip=2 repeated the first two rows'). It also cautions that 'other declared filters are forwarded as supplied; their effectiveness is not implied by the schema.' Every parameter receives some semantic treatment, though it doesn't enumerate the filters individually.

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 opens with a specific verb+resource+scope: 'Read current card rentals scoped by owner, renter or card_detail_id.' It clearly distinguishes this from full rental history with the explicit caveat 'This is not complete rental history,' which differentiates it from siblings like market_rental_history and rentals_v3_by_role. An agent can determine what this tool does without ambiguity.

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 gives useful context on what the tool does NOT do (not complete history, no auto-pagination, single logical GET) and notes that required inputs reflect 'tool policy as well as measured upstream requirements.' However, it never names a sibling tool to use when full history or pagination is needed, leaving the agent to infer the alternative. Context on limitations is present, but explicit routing to an alternative is absent.

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