Check AI budget

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds that it is 'Advice only, it never blocks' and describes the return shape (verdict, reason, recommendation), which goes beyond the annotations. This provides useful behavioral context for the agent.

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 sentences that are all essential and well-structured. It starts with the primary purpose, then gives usage timing, output shape, and parameter semantics without any fluff.

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 tool with one optional parameter, no output schema, and clear annotations, the description fully covers purpose, usage, behavioral nature, output format, and parameter meaning. Nothing important 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?

Schema description coverage is 0%, so the description must compensate. It explains the parameter's purpose: 'Pass estimated_next_tokens to test whether the next task would tip a token budget over.' This gives clear meaning to the single optional integer.

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 clearly states the tool is an 'Advisory gate' for checking whether the agent is about to exceed its AI budget. It specifies the resource (AI budget) and the action (check), and distinguishes itself from sibling tools like get_cost_summary or estimate_change_cost by focusing on a pre-run verdict.

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 says 'Call this before an expensive run,' providing clear context for when to use it. It also instructs to 'relay the verdict and let the human decide,' but does not mention when not to use it or name alternative tools, so it falls short of a 5.

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