browser_find_recipe

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

With no annotations, the description carries the full burden. It discloses the return shape at a high level ('stored action sequences') and that results are filtered by domain or task, but says nothing about behavior when no recipe matches, whether this is a pure read, or how many recipes come back.

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 short sentences with zero filler: the first defines the search surface, the second defines the return and its downstream consumer. Front-loaded with the action verb and free of hedging.

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?

No output schema exists, so the description must characterize returns — it does so by identifying recipes as runnable action sequences for browser_batch_actions. Minor remaining gap: the empty-result case and how to fall back (e.g., learn a new recipe) are unstated.

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 both parameters are already documented with examples. The description only restates the axes ('domain or task') the schema already defines, adding no filtering semantics, defaults, or interaction rules between query and domain.

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 ('searches ... for existing recipes on a domain or task') and names the payload it returns ('stored action sequences'). It also implicitly distinguishes itself from browser_save_recipe by being the retrieval side, though it never names that sibling or browser_get_site_memory.

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?

The phrase 'ready to run via browser_batch_actions' gives a clear follow-up path, so usage is implied: find a recipe, then batch-run it. However, there is no explicit when-to-use/when-not guidance and no differentiation from the closely related browser_get_site_memory sibling.

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