start_crew_run

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

With no annotations, the description covers creation of a run row, return of a ConversationalCard, behavior when sampling is unsupported, and idempotency with was_duplicate. Does not cover authorization or side effects, but provides substantial context.

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?

Four sentences, each adding unique value. Purpose is front-loaded. Could be slightly tighter but no redundancy.

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?

Covers purpose, usage context, parameter details, expected output, and edge cases (sampling not supported, duplicate detection). Lacks description of ConversationalCard structure, but output schema is absent and complexity is moderate.

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 coverage is 100%, baseline 3. Description adds value by explaining task_id as an idempotency key, recommending UUIDv5, and clarifying consequences of omission. Also notes token_budget default.

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?

Description clearly states 'Call this tool when the user wants to start a Crews Council run'. It identifies the specific verb (start) and resource (Crews Council run), distinguishing it from sibling tools like 'get_run' and 'list_runs'.

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 says when to call: when the user wants to start a run. Also provides guidance on LLM turn expectations and idempotency behavior. Lacks explicit exclusions or alternatives, but the domain is narrow enough.

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