grant_session_key

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

Annotations already declare non-readonly, non-destructive, non-idempotent, open-world. The description adds a genuinely useful trait beyond them: registration is not execution and server-side submission stays preparation-only, which tells the agent the grant will not fire a UserOperation. It stops short of stating auth requirements or what happens on re-registration of the same sessionId, which matters given idempotentHint=false.

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 sentences, front-loaded with the action and followed immediately by the scope caveat. The bracketed capability/tier/API metadata prefix is internal bookkeeping that costs tokens without helping an agent decide or call, but the prose itself is tight.

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?

A 14-required-parameter registration tool with no output schema and near-zero schema documentation leaves the agent unable to construct a valid call: no guidance on signature construction, address roles, allowance bounds, or chain constraints. Annotations cover the safety profile, but the operational surface is undocumented.

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 14% — just validAfter and validUntil are documented. The description adds nothing about the 14 required parameters: it doesn't explain sessionId vs sessionToken vs sessionPublicKey, what the signature signs over, nonce semantics, or the relationship between maxValuePerTx and maxTotalValue. With this many undocumented required fields, the description had to compensate and does not.

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: "Register a signed, bounded ERC-4337 session-key grant." That distinguishes it from the mutation siblings (revoke_session_key, session_key_status) and the execution siblings, though it doesn't explicitly contrast it with create_session or register_execution_delegation, which are the nearest alternatives.

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?

"Registration is not execution; server-side UserOperation submission remains preparation-only" scopes what the tool will not do, which implicitly bounds when to use it. But no alternative is named and no precondition is given for choosing this over create_session or request_execution_delegation.

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