pbi_wait_for

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

No annotations are provided, so the description must fully disclose behavior. It mentions polling and return format but omits critical details such as polling interval, default timeout, behavior when both text and textGone are specified, and error conditions.

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?

The description is extremely concise, conveying core functionality in a single sentence plus return type. No extraneous information, well front-loaded.

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?

Given 3 parameters, no output schema, and no annotations, the description leaves significant gaps: no explanation of mutual exclusivity of text/textGone, no default timeout, no behavior on timeout or errors. Insufficient for an agent to use reliably without additional inference.

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%. The description explains the purpose of text and textGone parameters. However, timeoutMs is not mentioned despite being a parameter, leaving its role unclear. Partial compensation but missing one parameter.

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 clearly states the tool polls body innerText until a specified text appears (text) or disappears (textGone), and returns a result object. It distinctly describes a waiting/polling utility, differentiating it from sibling tools that perform clicks, queries, or other actions.

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 description implies usage when waiting for text conditions but does not explicitly state when to use versus alternatives like pbi_state_probe. No guidance on when not to use or prerequisite conditions.

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