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

Annotation Contradiction: The description repeatedly calls this an 'exact owner-wallet read' and says 'Read tools return on-chain state', but the annotations declare readOnlyHint=false and idempotentHint=false. This directly contradicts the claimed read-only, idempotent behavior. While the description adds useful security context (no local wallet paths or keypair bytes), the contradiction makes behavioral disclosure unreliable.

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 overly long and contains boilerplate 'SAP MCP context' and 'SAP MCP execution guidance' paragraphs that are generic across the MCP and not tool-specific. While the opening sentence is effective, the repeated guidance about pricing, routing, and signer boundary adds unnecessary verbosity. It is not concise and does not make every sentence earn its place.

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?

The description covers the tool's purpose, the normalization output, and security guarantees, and an output schema exists. However, the annotation contradiction creates confusion about whether this is read-only, and the phrase 'when available' leaves unclear behavior for missing on-chain data. Given the complexity and the need to resolve conflicting signals, the description is not fully complete.

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 100%, so the schema already documents both parameters ('wallet' and 'includeSourceFragments') with clear descriptions including defaults. The main description does not add parameter-specific semantics beyond outlining output fields, which is acceptable but not compensatory. Baseline 3 is appropriate.

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 action ('Export a known SAP agent') and the specific output format ('OASF-style, machine-readable profile view'), with a stated purpose ('for agent directories and cross-runtime discovery'). It lists the normalized fields (identity, protocols, capabilities, pricing, x402 endpoint, metadata links, trust facts), which distinguishes it from generic getter tools like sap_get_agent or sap_get_agent_profile.

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 schema parameter description explicitly says 'Use sap_discover_agents or sap_agent_context first when the wallet is unknown', providing an alternative and a precondition. Additionally, the MCP context states 'Read tools return on-chain state; write tools require signer policy', giving clear guidance that this is a read tool and doesn't require signing.

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