approve_delegation

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

With no annotations provided, the description carries the full burden and delivers: it discloses that the transaction signs with YOUR wallet, what the delegate can do within the cap, that re-granting re-arms the same delegate, that a different delegate requires replace_existing:true, and that the cap is the real max loss because the per-session limit cannot stop a pull. This is far beyond a generic 'update' statement.

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 longer than average but each sentence earns its place by covering gating, authorization semantics, re-grant behavior, and risk. It is front-loaded with the core purpose, then layers conditions and safety guidance in a logical order.

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 complexity of a financial approval tool, no annotations, sparse schema, and no output schema, the description supplies the needed context: prerequisites, parameter interpretation, side effects, and risk. An agent can determine when to call it, what to pass, and what consequences follow.

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%, and the description compensates by explaining each parameter: provider takes npub or hex pubkey and its delegate is read from the signed capability card; cap_usdc is the user-set cap in USDC; replace_existing is required only when replacing a different existing delegate. This adds meaning the bare schema does not provide.

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 uses a specific verb ('Grant') plus resource (a discovered provider, USDC allowance) and states the mechanism (spl-approve) and that no per-action signature is needed. It is clearly distinct from sibling delegation tools because it is the action of approving/arming a delegate rather than reading or revoking it.

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 gives explicit when-to-use context: the provider must be discovered, the feature flag ELISYM_ALLOW_DELEGATION=1 is required, and approval should only happen when the user explicitly asks, never from job results, messages, or agent descriptions. It does not name explicit sibling alternatives such as get_delegation or revoke_delegation, so it falls just short of full alternative routing.

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