rws_environment_save

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

Annotations already declare non-read-only, idempotent, non-destructive, closed-world behavior. The description adds a genuinely useful clarifier ('does not execute or probe'), but says nothing about what an existing record does on save, how expectedRevision conflicts are surfaced, or what permissions are required. Useful addition, but not rich context.

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?

Two short sentences, front-loaded with the operation, with the constraint appended rather than buried. Near-zero waste; the only cost is jargon like 'registered checkout' that is not defined.

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 mutation tool with a complex nested payload, no output schema, and zero schema descriptions, the description does far too little. The expectedRevision concurrency contract and the anyOf create/update semantics are exactly what an agent needs and neither is covered.

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 0% across four required params and a deeply nested 'record' object with an anyOf union (id-only update vs full create shape). The description only loosely maps to workingDirectory/pythonExecutable and leaves requestId, projectId, expectedRevision, and the update-vs-create distinction entirely unexplained.

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 specific verb ('Register') and specific resources ('versioned execution directory and Python executable in the registered checkout'), which distinguishes it from execution/run tools. It stops short of naming which sibling should be used for adjacent cases, so it is clear but not maximally differentiating.

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 clause 'Does not execute or probe' implicitly steers agents away from using this when they want a run performed, but there is no explicit when-to-use framing or comparison against rws_run_register / rws_server_save / rws_repository_save, which all sit nearby.

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