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

With no annotations provided, the description carries the full transparency burden. It explicitly declares 'Read-only.' and explains the auth behavior: 'Unauthenticated callers get the signup step first.' It also mentions that output includes 'current limits,' giving a preview of side-effect-free behavior. This is good disclosure for a read-only tool.

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?

Four short sentences, each adding new information. The main outcome is front-loaded, followed by safety, usage, and auth context. No filler or redundant restatement of the schema.

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 simple read-only tool with 2 parameters and no output schema, the description covers purpose, usage, read-only behavior, and auth. It does not detail the exact output format, but it does say it returns a sequence of calls and current limits, which is sufficient for an agent to understand the result.

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 coverage is 50%: `tenant_key` has a description, but `kind` only has a type. The description compensates by explaining `kind` as 'a working tool of `kind`,' giving it semantic meaning. It also reinforces `tenant_key`'s signup context. The meaning is not exhaustive but covers the key gap.

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 starts with a precise outcome: 'Return the shortest ordered sequence of calls to a working tool of `kind`, with your namespace and a filled-in example already substituted in, plus the current limits.' This clearly identifies the action, the resource, and the output. It also differentiates from siblings by naming host.tool_publish and positioning itself as a prerequisite.

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 gives explicit guidance: 'Call this before host.tool_publish if you're not sure what a spec should look like.' This clearly states when to use the tool. However, it does not mention any exclusion cases or compare against other siblings like host.tool_list or host.registry_publish, so it misses the 'when-not' guidance.

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