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

The annotations declare non-read-only, non-idempotent, non-destructive, and closed-world, and the description adds substantially beyond that: it states no auth is required to call it, that the returned key is shown only once and cannot be retrieved, that the key is scoped to creating mappings/tests and reading balance but never billing, and that a new workspace has no calling capacity until a human verifies a phone. Rate limits and the retryAfterSeconds refusal shape are also disclosed, which is exactly the kind of operational detail annotations cannot carry. A 4 rather than 5 only because the description does not explain whether an abandoned or duplicate workspace can be deleted or reused.

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?

It is front-loaded with a one-sentence purpose before any section headers, and each block (use/do-not-use, return values, capability state, rate limits, related tools) maps to a distinct decision an agent must make. The only minor redundancy is that "It is the first step for an agent that has no TotalPath credential yet" restates the first USE WHEN bullet, which does not undermine an otherwise tightly structured definition.

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?

There is no output schema, so the description takes on the burden of describing the return payload, and it does so field by field (workspaceId, apiKey with its nq_ prefix and once-only visibility, keyPrefix, scopes). It also closes the loop on what happens next and why calling again is harmful, which is everything an agent needs to invoke this correctly on the first attempt.

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 single optional `name` parameter has 100% schema description coverage, so the baseline is 3, and the description adds no further guidance on it — nothing about naming conventions or whether an omitted name produces a default label. The return-field enumeration is valuable but belongs to output transparency, not parameter meaning.

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 first sentence names a specific verb and resource ("Create a new TotalPath workspace") plus a concrete outcome ("receive an API key"). This clearly distinguishes it from the surrounding read-oriented siblings such as getWorkspaceUsage and getClaimLink, so an agent can identify it without opening the schema.

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?

Explicit USE WHEN and DO NOT USE WHEN blocks give both the triggering condition (no credential yet, asked to set up from scratch) and the exclusion (already holding a key creates a second empty workspace). It also routes forward to the correct next tools (requestAnchorCode, verifyAnchorCode, getClaimLink), so the agent knows the sequencing, not just the entry point.

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