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

Annotations only indicate readOnly=false and destructiveHint=false, leaving room for additional context. The description adds that the tool requires owner opt-in, returns not-found otherwise, usage is metered to the owner, and no project token is needed—useful behavioral details beyond the annotations.

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?

Three sentences, each serving a distinct purpose: action, constraint/alternative, and preparation. No filler, front-loaded with the core functionality.

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 tool that invokes another, the description covers prerequisites, limitations, and the standard workflow. It omits expected return format, but since no output schema is present and the target varies, this is acceptable.

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 descriptions already explain each parameter (e.g., 'The toolName from a search_tools result'), and coverage is 100%. The description reinforces to get the argument schema from describe_tool but adds little semantic detail beyond the schema.

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 'calls a tool whose owner has enabled public invocation,' specifying the resource (publicly invocable tools) and distinguishing it from siblings by noting it works without a project token. It uniquely positions invoke_tool against describe_tool and search_tools, which are for discovery, not invocation.

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 explicitly says 'Only works for tools opted in by their owner; others return not-found (use describe_tool for how to call them with a token).' It also instructs to obtain project_slug/tool_name and argument schema from search_tools + describe_tool, giving clear when-to-use and preparation guidance.

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