create_intent

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

Annotations already declare write/idempotent/non-destructive, and the description adds the crucial behavioral fact that this is purely a record-keeping step with no signing or execution. The session_bound tag also hints at the session-scoped nature of the write, though auth requirements are not spelled out.

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 tight sentences, front-loaded with the verb and the key safety property, plus a compact metadata prefix. The bracketed metadata is dense but earns its place by conveying tier and authority endpoints; nothing is padded.

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?

Covers the essential semantic (this only records, never executes) which is the biggest risk of misuse, but for a nested-object write with no output schema and sparse param docs, it leaves gaps around what a successful call returns and what the session credentials are for. Adequate but not complete.

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 only 25%: the nested 'intent' object is effectively opaque (additionalProperties: {}) and sessionId, agentAddress, and sessionToken have no schema descriptions. The description never explains any of these inputs or what the intent object must contain, so it fails to compensate for the coverage gap.

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 and resource: 'create a durable FarmDashIntent', and adds that it records intent rather than executing. It clearly separates itself from prepare_intent/execute_approved_intent/simulate_intent, but does not distinguish itself from the similarly named create_mee_intent, so it stops short of a 5.

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 exclusions ('never prepares, signs, broadcasts, or executes') and tags the capability as preparation_only and session_bound, which tells an agent when not to reach for this. It does not route between this and other intent-creation siblings such as create_mee_intent or resolve_defi_intent, so no 5.

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