inspect_component_demo

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

With no annotations, the description carries the full burden and does well: it discloses asynchronous queueing, the fact that no execution wait occurs, the prohibition on arbitrary URLs, credentials, and destructive actions, and that retrieval never retries or bills another execution. It stops short of stating permission requirements, rate limits, or what happens when both selectors conflict beyond 'same record'.

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 most decision-relevant fact (queues and returns immediately) and ends with the sibling routing sentence, so structure is sound. The middle selector/auto-mode sentence is dense and slightly run-on, but every clause carries operational meaning.

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 6-parameter tool with no annotations and no output schema, the description covers the essential workflow: what is produced (run_id), what is forbidden, and where to get results next. The main gap is the unaddressed required parameters component and requested_checks, leaving an agent to infer their meaning from the schema names.

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%, so the description must compensate, and it only partly does. It clarifies implementation_name/implementation_url pairing and selection_mode semantics, but says nothing about component, source_id, or the requested_checks enum values (tab_click, accordion_toggle, etc.), which remain unexplained from the schema alone.

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 ('Queue a bounded Agent inspection') and states the immediate return value (TinyFish run_id) plus the key negative ('does not wait for browser execution'). This clearly separates it from get_component_demo_run, which is described as retrieving an existing run rather than queuing one.

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?

Explicitly routes the agent: use this to queue, use get_component_demo_run with the returned run_id for status and results. It also gives conditional rules for selector usage and restricts selection_mode=auto to the case where the user explicitly asks ComponentPilot to choose.

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