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

Rich disclosure well beyond annotations: states it does NOT broadcast, returns unsigned transactions, requires the user to sign and send both, itemizes the costs (rent, dev-buy ranges, 0.01 SOL fee), requires polling, and details the signer boundary (hosted builders never receive keypair bytes). This aligns with readOnlyHint=false and adds far more context than the annotations alone.

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 functional body is dense and front-loaded with the critical facts (unsigned, no broadcast, sign both, poll status). The appended 'SAP MCP execution guidance' block is somewhat verbose boilerplate that appears reused across tools, but it carries real routing and signer-boundary value, so it earns its place despite adding length.

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 14-parameter, paid-tier tool with an output schema present, the description is nearly complete: it covers return type, the do-not-broadcast warning, the required post-build actions, backing options, validation, pricing, and signer boundary. The only meaningful omission is explicit guidance distinguishing this from the escrow-based launch builder.

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 coverage is 100%, so baseline is 3. The description adds real value by clarifying the mutually exclusive backing structure — underlying+leverage+direction (single) OR 2-leg basket — and reiterating the dev-buy quote ranges and CUSTOM quote semantics. This goes slightly beyond the schema's per-field descriptions.

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 verb (build), resource (PerpsPad token launch backed by a leveraged perp), and output (UNSIGNED config + pool transactions), and it names the validation and status tools. However, it does not explicitly differentiate itself from its near-identical sibling sap_perpspad_build_escrow_launch, so an agent choosing between the two launch builders must infer the distinction.

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?

Provides a complete workflow: validate leverage against sap_perpspad_get_markets, build, sign and send BOTH transactions, then poll sap_perpspad_get_launch_status until live. The execution guidance adds routing instructions (estimate with sap_estimate_tool_cost, pay via sap_payments_call_paid_tool or x402). The notable gap is the absence of an explicit when-not-to-use statement contrasting the escrow launch sibling.

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