Read ADT Feed

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

Annotations already mark this readOnly/idempotent/non-destructive, and the description adds meaningful behavioral context: feed_path must start with /sap/bc/adt/, max_items is enforced client-side because some feeds ignore the server limit, and summary is a best-effort 500-character plain-text rendering of potentially escaped HTML. No contradiction with annotations.

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 organized into intro, args, returns, examples, and notes, with the most important purpose and sibling distinction front-loaded. Each note covers an edge case or constraint that matters for correct invocation, and there is no filler or redundant restating beyond what is useful for quick reference.

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?

Because there is no output schema, the description fills the gap by specifying the JSON return shapes for both listing and reading modes. It also covers response format semantics, path constraints, limit behavior, and alternatives, making it complete enough for an agent to invoke the tool correctly in both modes.

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 documents all three parameters with types, defaults, and constraints, so the baseline is 3. The description adds value by clarifying that feed_path must be an ADT href, that max_items applies only when reading and is enforced locally, and that response_format='json' yields the full structure. This extra nuance justifies a 4 rather than a 3.

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: 'List the ADT feeds available on this system... or read one feed's entries.' It also distinguishes itself from a sibling by directing short dumps to sap_list_dumps. The dual-mode behavior is stated upfront, so an agent knows exactly what this tool does.

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 gives explicit when-to-use guidance: omit feed_path to list feeds, pass an href to read one, and prefer sap_list_dumps or sap_get_dump for ABAP runtime errors. It also states the tool is not a general HTTP proxy and clarifies the path prefix requirement, leaving little to inference.

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