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

Annotations already declare the mutation profile (readOnly=false, idempotent=false, non-destructive, closed-world), so the description is not carrying the safety burden alone. It adds genuinely new facts beyond the annotations: the return payload (project_id + a one-time project_key), the PII-free constraint, and a security rule about not putting the key in a URL. It does not say what happens to pre-existing projects or whether the intake payload is mutated.

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 short sentences, zero filler, and the core action is front-loaded before the precondition and the security caveat. Each sentence carries distinct information (what it does, when to use it, a security rule).

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 state-creating mutation that returns a one-time secret, the description covers the important operational facts (persistence precondition, key handling). However, given 0% schema coverage on a deeply nested intake object and a required confirmation flag, the description leaves the agent guessing about how to populate the payload - a significant gap for this complexity level. No output schema exists, and the return values are at least summarized.

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 0% across 4 parameters, including a required nested `intake` object with ten sub-properties and a required `confirm_persist` boolean. The description explains none of them - it never says that confirm_persist gates the write, nor what the intake fields (goal, geometry, groundwater, etc.) mean or whether they must be PII-free. The 'PII-free' phrasing is the only indirect hint at parameter content.

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 names a specific verb and resource ('Create a persistent PII-free Project Workspace') plus what it returns, which is far more than the bare tool name conveys. It implicitly separates itself from intake-only siblings like project_intake and workspace_run_intake by requiring persistence intent, though it never names an alternative explicitly.

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?

'Use only after the user explicitly asks to persist project state' is a concrete precondition that tells the agent when to call it and, by implication, when not to (i.e., for exploratory intake). It stops short of naming which sibling to use instead when the user has not asked for persistence.

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