prepare_intent

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds useful context beyond that: it is preparation-only, session-bound, subject to gates, and never broadcasts. It stops short of saying what state preparation mutates or what happens to a previously prepared intent.

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 dense sentences with no filler, and every clause (capability, tier, endpoint, authority, gate order, no-broadcast caveat) carries information. The bracketed metadata prefix front-loads context but delays the actual verb until mid-sentence.

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 no output schema and the tool is not read-only, yet the description never says what preparation produces or how the result should be consumed. Combined with five undocumented parameters including a free-form nested object, an agent can select the tool but not confidently construct the call.

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 0%, so the description must carry parameter meaning and it largely does not. Only the API path incidentally reveals that intentId is the path identifier and 'session_bound' hints that sessionId/sessionToken are required; the nested `preparation` object and `agentAddress` are entirely unexplained.

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 ('prepare an intent') plus the gate ordering that precedes it, and explicitly disclaims broadcasting ('does not broadcast a transaction'), which distinguishes it from execute_approved_intent. It does not name the sibling tools it complements (simulate_intent, policy_check_intent), so differentiation is implied rather than explicit.

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?

Gives a clear precondition: call only after policy, simulation, and approval gates pass. That sequencing tells the agent where this sits in the workflow, though it never states what to do if gates have not passed or how to verify them.

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