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

The description states 'Read-only — reads Custody account directly from Solana RPC (on-chain),' but the annotations set readOnlyHint to false, which suggests the tool may modify state. This is a clear contradiction between the description and annotations. The description does add behavioral context (reads on-chain, snapshot only), but the contradiction undermines trust.

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 moderately concise. The first paragraph is succinct and focused on functionality. The second paragraph contains execution guidance that is generic SAP MCP boilerplate, which may be necessary for the ecosystem but adds length. Overall, it is not overly verbose, but the second paragraph could be condensed.

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 that there is an output schema (not shown but present) and the input schema is well-documented, the description provides sufficient context: it explains the return fields (funding rate, cumulative funding, OI), clarifies that it is a snapshot (not historical), and directs to the source of the required input. It is complete enough for an agent to understand the tool's role and output.

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?

The input schema has 100% coverage with descriptions for all 3 parameters. The description adds meaningful value beyond the schema: it advises to 'Pass the custodyAddress from sap_perp_markets' for the required param, and explains that the limit parameter behaves differently ('On-chain mode returns the current funding snapshot only'). The market param is described as optional display only.

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: 'Compute the current funding rate for an Adrena perpetual market from on-chain Custody account data.' It specifies the action (compute), the resource (funding rate), and the data source (on-chain Custody account). It also distinguishes from historical funding via a note, and references the sibling tool sap_perp_markets for obtaining the required custodyAddress.

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 provides a clear usage guideline: 'Pass the custodyAddress from sap_perp_markets.' It also indicates that the tool is read-only and that it returns only the current funding snapshot, not historical data. However, it does not explicitly contrast with sibling tools like sap_perp_position_info or sap_perp_trade_plan, nor does it specify when not to use it.

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