lbm_run_scan

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

Annotations indicate destructiveHint=true and readOnlyHint=false. The description adds crucial behavioral context: 'SPENDS user credits' and 'Always confirm with the user before running.' It also mentions the return state 'status="pending"'. No contradictions with annotations.

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 well-structured with section headers (WHEN TO USE, REQUIRES, RETURNS, NEXT STEP, CAUTION). Every sentence adds value; no verbosity.

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?

The description covers the full workflow: how to start, what is returned, what to do next, and caution about credits. Given no output schema, it provides enough context for agent usage.

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 100%, so baseline is 3. The description adds minimal extra meaning beyond the schema: it restates that project_id is required and mentions defaults briefly, but these are already in the schema. No significant new parameter insights.

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 action: 'To start a new monitoring scan for a project — sends prompts to all configured LLMs and collects responses.' It distinguishes from siblings like lbm_get_scan_status and lbm_list_scans.

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 explicitly provides 'WHEN TO USE', 'REQUIRES' (project_id from lbm_list_projects, project with at least one prompt), 'NEXT STEP' (poll lbm_get_scan_status), and 'CAUTION' (spends credits, confirm with user). This gives clear guidance on when and how to use the tool.

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