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

Beyond the annotations (idempotent, non-destructive, closed-world) it adds cost semantics ($0.001 per call, free on failure), the identity-matching rule that makes it an upsert, and the data-integrity guard that a stage with deals cannot be dropped. These are behavior details the annotations cannot express.

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?

Three sentences, front-loaded with the action and identity key, followed by the constraint and the cost. No filler. Slightly dense in the parenthetical, but each sentence earns its place.

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 4-parameter upsert with no output schema, it covers identity, mutation scope, constraints, and billing. It does not state what is returned (e.g. the saved pipeline and its id), which an agent would want after a create, but that is a minor omission.

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?

With only 25% schema coverage the description must carry weight: it maps pipeline_id/name to the record identity, position to 'position among the pipelines', and stages to order plus preservation-by-id-or-name. The richer per-stage semantics (outcome defaults, probability spreading) are covered by the nested schema description rather than the tool description, leaving marginal gap.

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?

States a specific verb pair (create or change) and resource (deal pipeline), and defines the upsert key explicitly: 'by pipeline_id, or the pipeline with this name'. An agent can distinguish it from crm_list_pipelines, crm_delete_pipeline, and crm_save_deal without opening any schema.

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 is clear this is the write path for pipelines, plus a concrete when-not condition: a stage that still holds deals cannot be dropped. It routes to crm_move_deal as the resolving alternative. It stops short of naming the read path (crm_list_pipelines) an agent would use to find pipeline_id first.

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