browser_replay

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

With no annotations, the description carries the full burden, and it does disclose two valuable traits: it does not perceive the page (cheap in tokens) and password fields are always typed by the human, implying a human hand-off step. It omits failure behavior (what happens if an element cannot be located), whether the recipe must pre-exist, and what the tool returns.

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 action, then mechanism, then parameter example, then the password caveat. Four short sentences with little waste, though the example JSON is slightly bulky for the information it conveys.

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-object, three-parameter tool with no annotations and no output schema, the description covers mechanism and token cost but leaves prerequisites (a recorded recipe must exist) and result/failure behavior unexplained; the 'snapshot' return behavior lives only in the schema.

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 only 33%, yet the description compensates for the most opaque parameter: 'params' is explained as overriding written texts, with a concrete example. 'name' is only implicitly the recipe identifier and is never stated as required, and no constraint on param keys matching recipe placeholders is given.

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?

Names a specific verb and resource: 'Repite una receta grabada' (replays a recorded recipe), and adds the mechanism (locates elements by role and name, executes steps without perceiving the page). An agent can tell this apart from browser_click/browser_type, but the description never names the sibling tools (browser_recipes, browser_record_start) that produce or list recipes.

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?

Usage is only implied: you call it when a recipe already exists, and the note about secret fields hints that a human is involved. There is no explicit 'use this instead of X' routing, no mention of how recipes are obtained, and no stated condition for when not to replay.

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