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

Annotations already carry readOnlyHint=true/destructiveHint=false, so the safety profile is covered. The description goes beyond that by declaring the mutation path lives elsewhere (accounts, human-driven) and by naming the exact data fields returned, which is genuinely useful context a caller can't infer from 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?

Two sentences, front-loaded with the returned data then the actionable guidance, with zero filler. The parenthetical examples ('eval runs, batch expansions') sharpen the trigger without bloat.

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, the description takes on the burden of describing the return contents and does so (plan, grant, spent, purchased balance). Read-only nature, out-of-scope mutations, and triggering context are all present, so an agent has everything needed to call it correctly.

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?

Only one parameter, and schema description coverage is 100% – the schema already explains the workspace slug, default-workspace override, and that it is ignored for workspace API keys. The description adds nothing about the parameter, so baseline 3 applies.

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?

Specific verb+resource (workspace's inference-credit position) and it enumerates exactly what is returned: plan, this month's grant and spent portion, and purchased balance. No sibling covers credit, and the agent can tell instantly what this yields versus the eval/dataset tools that consume spend.

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?

Explicitly names the trigger ('before proposing spend-heavy work (eval runs, batch expansions) when credit has come up') and the follow-up action ('cite the numbers'). It also carves out out-of-scope operations ('top-ups and plan changes happen in accounts, by a human'), though it does not name a sibling tool to redirect to.

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