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

With no annotations provided, the description carries the full burden. It explicitly states that the tool returns the ONE EIP-712 digest and that the server cannot sign, setting accurate expectations. It also mentions 'Auth required,' but does not detail the exact auth mechanism or any side effects (e.g., does it persist anything?). Since it is a preparation step, it likely doesn't mutate state, but that is not stated. Still, it provides useful behavioral context beyond the schema.

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 a single, dense sentence that packs purpose, key constraints, return value, next step, and a caveat (cannot sign) without any fluff. It is front-loaded with the action and resource, and the critical limitation (no signing) is highlighted. Every phrase earns its place; no redundant 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?

Given the tool's complexity (nested objects, 6 params), the description is adequate. It explains the high-level purpose, the return digest, the next step (confirm_delegation), and auth requirement. It does not detail the output schema (none exists), but that's not needed. It could mention that the digest must be signed with the account owner's key and that confirm_delegation will accept the signature, but that is implied. Complete enough for safe usage.

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 the baseline is 3. The description adds meaning by highlighting the key constraints: 'exact call allowlist' and 'optional rate limit', and clarifies the flow. It does not repeat parameter-by-parameter details, but the nested objects are well described in the schema. The description helps the agent understand which parameters are essential for scoping (calls, valid_until) and optional (rate_limit, valid_after). This adds value beyond the schema.

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 the tool's purpose: to prepare a scoped session-key grant for a Kernel smart account with exact call allowlist, expiry, and optional rate limit. It uses a specific verb ('Prepare') and resource ('delegation'), and differentiates it from siblings like confirm_delegation, renew_delegation, revoke_delegation, and get_delegation by emphasizing the preparation step and the off-chain signing requirement.

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 clearly explains when to use this tool: to prepare a delegation before signing, followed by confirm_delegation with the signature. It also states that this server cannot sign, guiding the agent to expect external signing. However, it does not explicitly mention when NOT to use it or alternatives like renew_delegation for renewals or revoke_delegation for revoking, but the context is clear enough for selection.

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