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

With annotations only providing readOnlyHint=false, destructiveHint=false, openWorldHint=true, and idempotentHint=false, the description goes far beyond by detailing the state transition (pending → approved → redispatch), the exact re-invocation mechanism (stored tool_name + params through the dispatch table), the failure semantics (stays APPROVED, not silently EXECUTED or PENDING), and retry guidance ('call this again to retry'). This richly complements the openWorldHint and aligns with the non-destructive annotation.

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 well-structured with purpose front-loaded, then mechanism, then failure/retry behavior, then a code reference. The final 'See wallets.approve_proposal' is a useful pointer. The middle sentence is long and packs several clauses, but each detail earns its place; it is dense rather than verbose.

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?

For a complex stateful tool with an output schema, the description covers purpose, preconditions (pending proposal, propose-mode, TTL), mechanism, post-conditions, and error/retry semantics. The only gap is the unexplained caller_id/approved_by semantics, which ties back to parameter coverage.

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 compensate. It helps for proposal_id by establishing the approval targets a 'pending PROPOSAL,' but it is completely silent on caller_id and approved_by — both have empty-string defaults and ambiguous purpose. An agent cannot tell whether to populate them, leave them empty, or whether they are server-injected for attribution or signature.

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 opens with a specific verb+resource+context: 'Approve a pending PROPOSAL within its TTL, then re-dispatch it (non-custodial control plane).' This uniquely identifies what the tool does and distinguishes it from siblings like propose_allocation, propose_template_update, and set_permission_mode — the agent immediately understands this is the approval step in a proposal lifecycle.

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 implies when to use this tool: when a proposal is in propose-mode ('see set_permission_mode') and pending, and it even explains when to call again on redispatch failure. It cross-references set_permission_mode as a precedent condition. However, it never explicitly states 'when NOT to use' or names a direct alternative for the same step, so guidance stops short of a full 5.

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