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

Annotations already mark it read-only, idempotent, non-destructive, and open-world; the description adds materially by disclosing the return payload, the read/cost posture, and the signer boundary ('hosted reads/builders never receive keypair bytes; value-moving results must be finalized locally when signing is required'). No contradiction with the annotations is present.

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 opening sentences are front-loaded and effective, and the category list is useful. However, the description then appends a long generic 'SAP MCP execution guidance' block that is duplicated verbatim inside the input schema and includes ambiguous phrasing such as 'Free read' alongside 'paid read-premium'. Not every sentence earns 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?

For a discovery tool with a rich input schema and an output schema, the description covers purpose, target disciplines, return content, pricing/routing behavior, and signing safety. An agent has what it needs to select this tool, pass the right query/category/limit, and understand the follow-on execution path.

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 already covers all 3 parameters, so the baseline is 3. The description adds real value for the category parameter by enumerating the valid prefixes and what each domain represents, e.g. 'sap_phoenix_ (Phoenix perps)', 'jupiter_ (swaps)', 'sap_sunrise_ (Sunrise asset gateway)'. Query and limit semantics are mostly left to the schema, which is acceptable.

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?

States a concrete verb and object: 'Search the SAP MCP tool catalog (420+ tools) by keyword' and specifies the result shape ('top-K matching tools with their name, description, and full input schema'). It also names sap_call_tool as the follow-on, which clearly distinguishes this discovery tool from the hundreds of execution-focused siblings.

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?

Explicitly routes the agent: 'Use this to discover tools before calling them via sap_call_tool.' The category enumeration gives practical filtering guidance. It does not spell out exclusions, such as when the agent already knows the exact tool name and should call sap_call_tool directly, so it stops short of a 5.

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