Generate a contract

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

No annotations are supplied, so the description carries the full burden. It usefully discloses that requests can fail validation and that error.suggestion should be honored, and it forbids fabricating party data. But it omits key behavioral facts: whether the contract is persisted and retrievable via get_contract, whether generation is idempotent, the cost or latency, and any auth or rate-limit expectations.

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?

Three sentences, each carrying distinct load: what is generated, what must be collected before calling, and how to recover from validation failure. It is front-loaded with the tool purpose and contains no filler.

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 16-parameter tool with nested objects, five enums, and no annotations or output schema, the description covers purpose, a data-fabrication prohibition, and error handling, but leaves the return value undocumented (though the schema notes pdf returns a 1-hour signed URL) and says nothing about persistence or follow-up retrieval. It is adequate but not complete for a tool of this complexity.

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% and the schema already documents conditional fields such as nda_type, deliverables, and fee, so the baseline is 3. The description adds only marginal meaning: the type enumeration is repeated and 'never invent party names, addresses, dates, or amounts' implies that certain fields must be sourced from the user rather than inferred, but no field-level format or dependency detail is added.

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 states a specific verb and resource ('Generate a ... contract') and enumerates all five supported contract types, so the agent knows precisely what this tool produces. It does not explicitly name the siblings list_contract_templates or get_contract, so the distinction from them is only implied by the verb.

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 gives a firm precondition ('Collect all required fields through conversation before calling — never invent party names, addresses, dates, or amounts') and an error-recovery rule, which are genuinely useful usage constraints. However, it never says when to use this tool versus list_contract_templates or get_contract, leaving alternative routing to inference.

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