System

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 'manage the server' which implies potential mutations (e.g., reindexing), but doesn't specify permissions, side effects, or response formats. For a system administration tool with zero annotation coverage, this is inadequate—critical details like whether actions are destructive or require special auth are missing.

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 concise and front-loaded, listing key functions in a single sentence. Every phrase ('check status', 'get indexing info', etc.) contributes to understanding the tool's scope. However, it could be slightly more structured by separating read vs. write operations or grouping related functions.

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 tool's complexity (system administration with potential mutations), lack of annotations, no output schema, and incomplete parameter documentation, the description is insufficient. It doesn't address critical aspects like error handling, security requirements, or what 'manage the server' entails. For a tool with this scope, more comprehensive guidance is needed.

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 50% (only 'maxDepth' has a description). The description adds no parameter-specific information beyond what's implied by the action enum values (e.g., 'reindex' relates to 'get indexing info'). It doesn't explain parameter interactions or provide examples. With low schema coverage, the description fails to compensate meaningfully, resulting in a baseline score.

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 as 'System administration' with specific functions: 'check status, get indexing info, vault structure overview, and manage the server.' It uses specific verbs (check, get, overview, manage) and identifies the resource (server/system). However, it doesn't explicitly differentiate from sibling tools like 'vault' or 'workflow' which might have overlapping administrative functions.

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 no guidance on when to use this tool versus alternatives. It lists functions but doesn't specify contexts, prerequisites, or exclusions. For example, it doesn't clarify if 'manage the server' includes operations that might conflict with sibling tools like 'edit' or 'workflow'. This leaves the agent with minimal usage direction.

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