run_recipe

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

With no annotations, the description carries the full burden and meets it: it discloses that steps run exactly as given in order, that it stops at the first error and returns all prior results plus the failing step, and that saving captures every session tool call, not just this call's steps. These are non-obvious behaviors an agent could not infer from the schema.

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-loaded with the core action, then the operational caveats in descending importance. It is dense and long, but nearly every clause adds a distinct operational fact; the parenthetical examples are slightly verbose but still load-bearing.

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 nested, no-annotation, no-output-schema tool, the description covers execution order, error semantics, return-on-failure behavior, replay, and save scope. 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?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning beyond the schema: fingerprint replays and auto-updates a success/failure counter, and save_as persists the whole session's calls rather than just steps. The mutual-exclusivity and the need to include a read_page before an index-based step are also clarified.

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 ('Execute a sequence of OctoLimb tool steps in one call') and immediately scopes it as a batching primitive, distinguishing it from the single-step siblings like click_element and go_to_url. It also carves out its relationship to find_recipe (replay) explicitly.

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?

Gives explicit when-to-use conditions ('batch obvious action chains', 'replay steps returned by find_recipe') and a when-not ('use only when the task requires acting on a real website'). It also states the selection rule between the steps and fingerprint parameters.

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