sap_write_code_safe

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

With no annotations, the description carries the full burden and provides strong behavioral disclaimers: validation, retries, compatibility, and deployment behavior are endpoint-dependent; the name does not guarantee safety; the public connector lacks Python-bridge/ADT capabilities. This goes well beyond a bare proxy description, though it leaves the eventual behavior still somewhat opaque.

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?

Four sentences, each carrying information: the forwarding behavior, the endpoint-dependent safeguards, the connector limitations, and the schema-incompleteness warning. Slightly dense and jargon-heavy (Python bridge, abap://syntax-rules) but not padded.

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 an empty input schema, no output schema, and no annotations, the description should enable an agent to invoke the tool; instead it only says to verify the backend contract and required arguments externally. It does not state what to send, what endpoint configuration is needed, or what response to expect, so the agent cannot call it correctly from this definition alone.

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 is empty, so there are no parameter details to add; the 0-parameter baseline applies. The description still adds value by explicitly warning that required arguments exist and that the current schema is incomplete, telling the agent not to trust the empty schema.

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 action and target ('Forward a request to the configured /write_code_safe endpoint'), which clarifies the tool is a forwarder rather than an implementation of safe writing. It distinguishes itself from naive readings of the name and from the public Node connector, though it does not explicitly name sibling tools like sap_write_code.

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?

No when-to-use or when-not-to-use guidance relative to siblings is provided. The cautions about validating the backend contract are safety warnings, not selection criteria, and the tool never says what conditions should lead an agent to choose this over sap_write_code or sap_patch_code.

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