Run Daily Scan

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

With no annotations, the description carries the full burden of behavioral disclosure. It discloses that the tool is deliberately slow ('Slow (minutes, deliberately)'), which is valuable. However, it doesn't describe the output, side effects, or failure modes. It implies it updates data via 'force a refresh' but doesn't clarify whether it blocks or returns results. For a trigger tool, this is above minimal but incomplete.

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 concise and well-structured. The first sentence states the core action and purpose. The second paragraph provides context and a usage warning without unnecessary fluff. All information is front-loaded, making it easy for an agent to parse quickly.

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 one optional parameter and an output schema, the description is incomplete. It fails to explain the use_llm parameter, which is a significant gap. It also doesn't describe the return value or what happens after the scan runs (e.g., whether it blocks or returns immediately). While the output schema might cover return structure, the description doesn't connect the tool's behavior to its effect. Given the simplicity of the tool, more could be done.

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?

The only parameter, use_llm, has 0% schema description coverage, and the description does not mention it at all. The agent is left to guess what 'use_llm' controls (likely whether to use LLM processing during the scan). Since the description adds no meaning beyond the schema, and the schema itself has no description, the parameter is effectively undocumented.

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's purpose: run the daily crawl now instead of waiting for the scheduled job. It uses a specific verb ('run'), names the resource ('daily crawl'), and distinguishes itself from the scheduled job by emphasizing manual initiation. It also explicitly mentions 'force a refresh', which helps differentiate from sibling tools that read data.

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 provides clear usage context: 'Normally Task Scheduler calls this via `fbmarket-scan`; use this tool when you want to force a refresh.' This tells the agent when to use it (forced refresh) and implies when not (normal scheduled runs). It also warns about slowness, which is a practical usage guideline. However, it doesn't explicitly mention alternative tools, but the context is sufficient for a unique trigger action.

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