cfg_edit

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

No annotations provided, but description clearly states it does not write to disk, which is a key behavioral constraint. For a tool with no annotations, this disclosure adds value, though additional info on permissions or side effects would be better.

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?

Extremely concise: two sentences plus a parameter list. Every sentence adds value—purpose, behavior, parameter explanations. No wasted words, front-loaded with the core action.

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 validation tool with 3 parameters and an output schema (implied but not shown), the description covers the action, parameters, and key behavior. Could mention what happens on validation failure or diff formatting, but given the tool's focused purpose, it is largely 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 coverage is 0%, but description adds rich semantics: existing_cfg as 'current on-disk configuration text', change_description as 'short natural-language description', new_cfg as 'LLM's rewritten configuration text'. This fully compensates for missing schema descriptions.

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?

Clearly states it validates an edited OpenSIPS config and returns a unified diff. 'Validate' + 'return unified diff' is specific verb+resource, and it distinguishes from siblings like cfg_validate (no diff) and cfg_diff (no validation).

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 says 'Does not write anything to disk — the caller chooses to persist after reviewing the diff.' This tells the agent this is a preview step before persisting. Could be improved by contrasting with cfg_validate or cfg_diff for even clearer when-not-to-use.

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