config

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions side effects (ensure_home 'creates profiles/secrets/logs/state + default config.toml') and a security-relevant trait ('body never returned' for put_secret). However, it does not explain reversibility of delete_profile, required permissions, or error/return behavior in detail.

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 a dense, information-packed two-sentence block. It front-loads the purpose and then provides a compact op reference. Every sentence and most clauses add value, though the run-on style with many pipe-separated lists makes it slightly hard to parse quickly.

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 the complexity (14 parameters, multiple operations, no output schema, no annotations), the description covers the core usage patterns and important parameters well. It leaves some operations (get, list_profiles, delete_profile) under-specified but still gives a solid mental model for when and how to use the tool.

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 has 14 parameters with no descriptions, so the description must compensate. It maps key parameters to operations: put_secret name= content=, put_profile name= transport=local|ssh|winrm with host/username/port/auth/ssh/winrm/defaults/caps. This adds substantial meaning beyond the schema. Some parameters (label, body, defaults) are only partially or implicitly covered, so it is not a perfect 5.

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 clearly states the tool's purpose: 'Self-configure MRC_HOME for the agent' and enumerates the supported operations (op=home|ensure_home|...). It uses a specific verb ('self-configure') and resource (MRC_HOME), and it distinguishes itself from sibling tools (endpoint, exec, fs, etc.) by focusing on configuration rather than runtime actions.

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 provides context on when to use the tool (to set up MRC_HOME without hand-editing files) and references a follow-up step with the sibling tool: 'Then endpoint open profile=<name>.' It does not explicitly state when not to use it or list alternative tools beyond endpoint, but the op list and examples give clear usage guidance.

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