web_task

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

There are no annotations, so the description carries the full burden of behavioral disclosure. It reveals critical traits: the tool is a durable ledger, it does not drive a browser itself, it must not auto-resend unknown submissions, and media availability must be observed rather than assumed. This is strong behavioral context. It does not explain each action's side effects, but the disclosed constraints are unusually valuable.

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 compact and front-loaded with the core identity, then the workflow pipeline, then critical safety constraints. Every sentence contributes information, and there is no filler. The phrasing is dense and somewhat cryptic, but structurally it is efficient and well-ordered.

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 tool with 9 undocumented parameters, 8 actions, no output schema, and no annotations, this description is too sparse to fully support correct invocation. It gives excellent safety constraints but does not specify what each action requires, what parameters are valid for each action, or what response an agent should expect. The workflow hints are useful but incomplete for a tool of this complexity.

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%, and the description adds almost no meaning for the nine parameters. It references workflow steps like prepare, bind, claim, collect, and accept, but does not explain parameters such as url, text, taskId, tabId, browserId, evidence, or revision. The phrase 'claim BEFORE Send' is cryptic and 'Send' is not even an action in the enum. The description does not compensate for the schema's total lack of parameter documentation.

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 identifies web_task as a 'durable ledger for agent-operated ChatGPT browser tasks,' giving a specific resource and role. It also clearly states what the tool does NOT do: it does not control a browser or send prompts itself, which helps an agent distinguish it from action-taking tools. However, it does not explicitly name or differentiate against sibling tools, so the distinction is implicit rather than direct.

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 gives an explicit workflow order: 'prepare -> bind -> claim BEFORE Send -> collect visible result -> independently accept.' This tells an agent how the actions are meant to be sequenced. It also adds important conditions: 'Unknown submission must never be automatically resent' and 'Image/video availability must be observed, not assumed.' It lacks a direct statement of when to choose this tool over a sibling, but the protocol guidance is far above minimal.

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