update_deal_stage

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

With no structured annotations provided, the description carries the full burden of behavioral disclosure. It clearly flags the operation as 'WRITES DATA' and notes the reason is 'audited', which conveys the mutation side effect and accountability. It does not discuss reversibility or downstream effects, but the essential behavioral traits are explicit.

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 purpose and guardrail are front-loaded in the first sentence, followed by a structured argument block. The embedded JSON is somewhat dense but necessary because the structured schema provides no parameter details, and every part contributes to a correct invocation.

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 combines a clear purpose, an explicit usage precondition, full parameter documentation, and an existing output schema. For a focused stage-update tool, this provides enough context for an agent to select and invoke the tool correctly without needing additional assumptions.

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 actual input schema is a generic 'arguments' bag with 0% schema description coverage, so the description must fully compensate. It does so by embedding a complete parameter spec: deal_id with pattern, stage with enum values, and reason with min/max length and audit semantics. This gives the agent all the parameter meaning it needs.

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 opens with a specific verb-resource pair: 'Move a deal to another pipeline stage.' This unambiguously identifies the operation and clearly differentiates it from sibling read-focused tools like get_deal, list_deals, and pipeline_summary.

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 states when to call the tool: 'only call when the user explicitly asked for the change and provided a reason.' This functions as both a when-to-use and when-not-to-use guardrail, which is especially valuable for a write operation.

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