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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=true, idempotentHint=false, openWorldHint=true) by disclosing the billing model (fixed per-call price vs provider price + 35%), that max_cost_usd must cover estimated cost and needs sufficient balance, that provider failures are not charged, the 25-second pending-run polling window, and the no-retry rule for truncated results. This is exactly the operational context the annotations cannot carry.

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?

Front-loads purpose in the first sentence and packs each subsequent sentence with distinct operational facts (pricing, cap, failure handling, polling, retry policy). Dense but mostly waste-free; the final sentence about model REST endpoints feels tacked on.

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 covers the critical lifecycle concerns an agent needs: cost semantics, failure/refund behavior, pending-run polling, and handoff to get_run. It does not describe what a successful run returns (run id, result payload shape), which is the main remaining gap for a tool of this complexity.

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 one nested field well (input.max_cost_usd as a catalog spending cap with balance requirements) and implies tool is the public tool name and input is that tool's input, but it never documents the general shape or format of the top-level 'input' object or how to source a valid tool identifier.

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 concrete verb and resource ('Execute a public tool') and names the execution path ('REST billing and access controls'), which cleanly separates it from siblings get_run, inspect_tool, and search_tools. The 'Inspect first' instruction further disambiguates the execution role.

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?

Names explicit alternatives and conditions: 'Inspect first' routes to inspect_tool, 'use get_run to check later without starting another execution' routes to get_run, and 'Truncated or unsupported results must not be retried' gives a clear when-not rule. It stops short of spelling out how to discover valid tool names (search_tools), but the routing guidance is otherwise strong.

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