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

Annotations already cover safety (readOnlyHint, destructiveHint=false, openWorldHint, idempotentHint=false), so the bar is lower; the description still adds real behavioral context by explaining the handle model, the inline-vs-preview threshold behavior, and that results carry suggested next ops. It does not describe failure/error behavior for a bad op or unreachable URL, which would be the remaining gap.

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 action and result contract, followed by a compact example that demonstrates the chain. No filler and nothing duplicated from the schema.

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?

An output schema exists, so return values needn't be spelled out, and the description correctly focuses on the handle/indirection model that an agent must understand to chain ops. It is nearly complete, missing only error-handling and the explicit boundary against run_pipeline/run_recipe.

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 100% and each parameter (op, args, input, input_type, inline_max_tokens) is documented in the schema, so the baseline is 3. The description reinforces semantics by showing op+args together and input receiving a handle from a prior result, but it introduces no syntax or constraint details beyond what the schema already provides.

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 states a specific action and resource: 'Run one operation and get its result as a handle', then enumerates what the handle contains (type, size, estimated tokens, value or preview, suggested next ops). The word 'one' implicitly contrasts with run_pipeline/run_recipe and it routes to discover() for op ids, but it never explicitly names those siblings, so an agent must infer the boundary.

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?

A concrete two-step example (invoke(op="fetch") then invoke(op="html_to_text", input=handle)) demonstrates the idiomatic chaining pattern and how results are fed forward, plus a pointer to discover() for valid op ids. There is no explicit when-not guidance or direct comparison to run_pipeline/run_recipe, so usage choice is guided by example rather than stated rules.

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