config

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

The description says setup_reset 'clear credentials and config, return to awaiting_setup', yet destructiveHint is false. This is a direct contradiction: clearing credentials and config is a destructive operation. The description also implies browser/relay-based setup activity that sits uncomfortably with openWorldHint=false, further reducing trust in the annotation profile.

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 concise, front-loaded action list where every line adds relevant behavioral information. It avoids filler and packs no-op, alias, and effect details into very few words.

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?

The description covers all seven actions, including edge-case behavior such as aliases and no-ops, while the output schema likely covers return shape. Completeness is undermined by the contradiction between the described clearing/setup behavior and the annotations, so the contextual picture is not fully reliable.

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 schema already covers all parameters, and the description adds meaningful semantics for the action enum values, including side effects, aliases, and no-ops. It clarifies that setup_start connects to the force parameter and that set is effectively informational for Notion, going beyond the schema's minimal 'Action to perform' description.

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 function verb and resource domain: 'Manage server configuration and credential state.' It clearly enumerates the action dispatch behavior, though it does not differentiate itself from sibling tool config__open_relay, so it stops short of full sibling differentiation.

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 action list provides clear contextual guidance, such as 'setup_complete: re-check credentials after external config changes', 'cache_clear: no-op for notion', and 'set: notion has no mutable settings'. It gives clear context but does not explicitly state when to prefer this tool over alternative sibling tools.

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