nayori_client_create_job

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

Annotations indicate write (readOnlyHint false) and non-destructive (destructiveHint false). The description adds substantive behavioral details: criteria hashing and commitment, default evaluator, expiry defaults, no fund movement, server cannot fund, and that broadcasting does not confirm. It also clarifies that the job id is obtained via nayori_tx_status, which is extra context. It does not contradict annotations. Minor gap: no explicit mention of permission requirements or reversibility, but given the annotations and richness, a 4 is fair.

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 compact but dense, with critical operational constraints front-loaded ('WRITE (mainnet)', 'Act as a CLIENT'). It avoids fluff and every sentence carries operational value. While long, it matches the complexity of a job-creation tool; the structure is logical, moving from purpose to mechanism to constraints. No wasted words.

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 tool with 6 parameters, no output schema, and significant side effects, the description covers essential context: funding limitations, default evaluator, expiry window, and return semantics (txid vs confirmation). The reference to 'nayori_tx_status' for job id is helpful though slightly cryptic. It adequately equips an agent to avoid common errors (e.g., expecting funding, misinterpreting broadcast as confirmation). Minor omission: no explicit statement about transaction speed or gas, but given the overall thoroughness, a 4 is appropriate.

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 describes parameters with decent coverage (83%). The description adds meaning: acceptanceCriteria must be kept verbatim due to hashing, description has a commitment appended, expiry default, and provider optionality. It clarifies that the criteria are hashed, which is not in the schema. This goes beyond the schema and compensates for the remaining 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?

States a specific verb ('create'), resource ('evaluable Nayori job'), and scope ('on the escrow', 'Act as a CLIENT'). It clearly distinguishes from sibling tools like nayori_apply_to_job and nayori_client_assign_provider by emphasizing the creation action and the criteria hashing mechanism. An agent can immediately tell this is for initiating a job from the client side.

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 context for when to use: as a client on mainnet for creating a job. It warns that the server cannot fund jobs and that funding is a human wallet action, guiding the agent away from expecting fund transfers. It does not explicitly name alternative tools for other actions, but the role and action are unambiguous given sibling context. Slight deduction for not explicitly naming what not to use.

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