AIMarket — live agent marketplace

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

With no annotations provided, the description fully bears the transparency burden. It discloses trial allowance limits, the signed receipt returned, the 402 response after allowance exhaustion, and that the tool reports rather than fabricates results. It also covers the payment parameter requirements. It could be more transparent about side effects or the contents of the receipt, but it is substantially informative.

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 two sentences: the first is a crisp statement of purpose, and the second packs trial and payment details into a dense but efficient format. Each clause contributes new information, though the second sentence is long and slightly run-on, which mildly hampers readability.

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 7 parameters, two nested objects, no output schema, and no annotations, the description covers the core behavior: how to invoke, the trial and paid flows, and error reporting on 402. It does not detail the exact structure of payment_authorization or the signed receipt, but the combination of description and schema gives a workable understanding of the tool.

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?

The input schema covers only 4 of 7 properties with descriptions (57% coverage). The three payment-related parameters (payment_channel, payment_channel_secret, payment_authorization) have no schema descriptions, but the description compensates by explaining their roles in paid and escrow access. It adds meaning beyond the schema, particularly for the undocumented parameters.

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 the tool's function: to 'Invoke a capability found via market_search.' The verb 'invoke' is specific and the resource is well-defined. It distinguishes itself from the sibling market_search by explicitly tying invocation to a prior search result, making its role unambiguous.

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 explains when to use the tool—after finding a capability via market_search. It also delineates the two access modes: trial invokes (no wallet, key, or channel) and paid access (payment_channel with secret, plus payment_authorization for escrow). However, it does not explicitly state when not to use it or mention exclusions, leaving a slight gap.

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

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

With no annotations, the description must carry behavioral disclosure. It explains that the tool only searches and returns matching capability ids, prices, and source_hub, and the phrase 'to pass back to market_invoke' clarifies that it does not itself perform the invocation. It doesn't describe ordering or empty-result behavior, but the core search behavior is transparent.

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?

Two sentences, no fluff. The first sentence states action, second covers optional filters and outputs; every clause 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?

For a straightforward search tool with full schema coverage and no output schema, this description is sufficient. It tells the agent what filters are available, what results will contain, and how to use the result with the sibling tool.

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?

The input schema already describes all four parameters with 100% coverage. The description adds modest context by naming category and budget as optional filters and noting the return fields, but it doesn't explain parameter semantics beyond the schema, so the baseline of 3 applies.

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: 'Search this hub's capability catalogue by intent.' It clearly identifies what is searched and the key input, and the return of source_hub for market_invoke distinguishes it from the sibling market_invoke tool.

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 implies this tool is the discovery step before market_invoke by returning a source_hub to pass along. It doesn't explicitly state when not to use it, but the context is clear enough for an agent to choose between searching and invoking.

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