pipeline_stages_upsert

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

With only destructiveHint=false provided, the description carries real weight and adds material context beyond the annotation: probability is validated to 0-100 "here", it is the single entry point for the default, and the outcome flag drives terminal behaviour through deals_mark while stage-to-status derivation remains fixed mechanism. It does not disclose whether patching overwrites unspecified fields, which matters for an update path, so it is strong but not complete.

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 mutation intent and the field list are front-loaded in the first clause, and the patch/append rule follows immediately, so the important content is not buried. The trailing §6b and "§6b Fixed" references consume space without conveying meaning to an agent that lacks the spec.

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 an 8-parameter write tool with no output schema and only a single boolean annotation, the description should say more about which fields are required for create versus patch and what idempotencyKey does. The core mechanics are explained, but required-field behaviour and the scope of a patch are left to inference.

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 does explain name, sort, probability (0-100, validated), outcome (won/lost) and stageId (patch vs append). It says nothing about workspaceId, pipelineId, or idempotencyKey — three of eight parameters — leaving required-parameter roles and retry/idempotency semantics undocumented in both places.

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 concrete verb+resource pair ("Lege eine Phase an oder bearbeite sie" = create or edit a stage) and enumerates the fields it governs, so the agent knows exactly what domain object is being written. It does not name or differentiate itself from the obvious sibling pipelines_upsert, and the §6b cross-references are opaque without the external spec, which keeps it below a 5.

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?

It gives explicit mode selection: "Pass stageId to patch, omit it to append", which is exactly the branching an agent needs to choose between update and create. It also notes that the outcome flag makes stage entry terminal via deals_mark, hinting at downstream behaviour, but it names no alternative tool and gives no exclusion criteria for when to use this versus pipelines_upsert.

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