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

Annotations only cover safety flags (readOnlyHint=false, destructiveHint=false, idempotentHint=false); the description goes well beyond them with lifetime rules ('expires within 30 minutes and never outlives the parent token'), a handling constraint ('pass it to the CLI process environment, never a file, log, user-facing message or unrelated service'), and revocation semantics ('revoking the parent does not cascade'). This is exactly the behavioral disclosure a token tool needs.

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 output is front-loaded with the core action and every sentence carries distinct information (lifetime, handling, exclusions, revocation). It is slightly denser than necessary, with the terminal caveat restated across two sentences, but there is no filler.

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?

With no output schema, zero parameters, and only safety annotations, the description carries the full burden and does so: what it creates, its lifetime, where it may be placed, when not to call it, and its revocation behavior are all covered. Nothing an agent needs to invoke it correctly is missing.

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 tool takes zero parameters, so there is no parameter surface for the description to compensate for; baseline 4 applies. The description instead clarifies the implicit inputs (host terminal capability, user upload intent) that govern whether the call is valid.

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?

States a specific verb and resource ('Create a workspace-scoped credential for the SPACE CLI'), scoping the artifact precisely enough to separate it from siblings like create_upload_link and create_upload_session. An agent can tell what is produced without opening any 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 preconditions ('only when the host supports a local terminal and the user requests an upload') and exclusions ('This is not needed for browsing or feedback, and does not give a chat-only host a terminal'). This names the when, the when-not, and the anti-pattern in one place.

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