toolbox

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

With no annotations available, the description carries the full burden, and it delivers. It discloses output expiration ('expire after 30 minutes'), bounded output size with paging ('next_offset'), and the enable/program behavior. The 'even when the MCP client ignores the raw tool list' statement adds infra-level transparency. The description does not fully disclose all safety or side-effect nuances of call/enable/disable, but it is far beyond a minimal explanation.

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 has a clear, structured format: a purpose sentence, then one per operation, and then the profiles. Every sentence adds new operational detail; no filler. Front-loaded with the core actiom, and compact despite covering many features.

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 no output schema, seven operations, and nine parameters, the description covers each operation with its relevant parameters, paging / workspace / expiry behavior. It also explains the 'profiles' concept and provides a list of all profiles. The only small missing pieces are explicit return shapes for describe/call, but the description already hints that 'output' returns captured raw output and the gateway is otherwise well explained.

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?

Even though the schema covers 100% of parameters with descriptions, this plumbing meaningfully supplements that. It maps operation arguments to parameters (e.g., 'output_id', 'output_offset', 'therapy'), explicitly tells the agent to 'Use operation=describe first when the schema is any', lists profiles, and 'large records report next_offset' enriches semantics. This is more than baseline schema coverage.

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 verb+resource account: 'Discover and call any AgentTool capability without loading every tool schema into the model context.' It clearly identifies this as a gateway/dispatcher distinct from the concrete sibling tools (read, edit, grep, etc.), and gives a compact summary of what it provides.

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?

Usage is spelled out operation by operation: 'Use operation=describe... then... operation=call...', 'Use operation=output...', and 'Use operation=list...' It even adds a strong preference note: 'Prefer describe/call because they work even when the MCP client ignores dynamic tool-list changes.' Missing an explicit when-not-to-use or direct comparison to the sibling tools, but the intended gateway use case is clear.

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