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

Annotations show readOnlyHint=false and destructiveHint=true, so the mutation/safety profile is already declared. The description meaningfully adds behavioral context: it reveals the underlying on-chain flow (creating escrow, funding USDC, executing) and notes the buyer agent derivation nuance, which is not visible in the annotations. This goes beyond the annotations and helps the agent anticipate side effects.

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 denotes the action and outcome, the second clarifies the intended audience and positions it as a comprehensive bridge. No redundant wording, and the important behavioral detail (on-chain escrow/funding) is front-loaded. Every sentence 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?

There is an output schema (not supplied in the prompt), the annotations clearly mark it as destructive/non-readonly, and the input schema provides high coverage. The description covers the end-to-end process and audience. It doesn't mention required wallet/funding prerequisites or cancellation behavior, but for a high-level convenience tool with schema and output schema present, this is adequate. Slightly short of perfect due to missing explicit fallback guidance.

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 description coverage is 100%, so all three parameters are already described (capability, task_input, max_price_usdc). The description's phrase 'Searches by capability' reinforces the meaning of the first parameter but adds no new syntax or format details. The default for max_price_usdc is in the schema. Baseline 3 is appropriate when the schema carries the weight; the description doesn't need to add more.

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 a specific verb ('Hire'), a resource ('an agent from the marketplace'), and a multi-step workflow ('searches by capability, creates escrow, funds the escrow on-chain, executes the task, and returns the result'). It also explicitly identifies its role as a one-call bridge for local orchestrators, distinguishing it from lower-level sibling tools like data_session_attach_escrow or data_session_fund. The description provides strong differentiation.

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 names its target audience ('local orchestrators like Claude Code, Cursor') and frames itself as a high-level convenience bridge. The input schema's description adds that the buyer agent is derived from the authenticated principal, never from arguments—valuable guidance. However, it doesn't explicitly say when NOT to use it, e.g., when to use the lower-level data_session_fund or discover_agents steps instead. Still, clear context is provided.

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