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

With no annotations, the description carries the behavioral burden and does meaningful work: it declares that all chapters return verified dys-cli sales-prototype numbers and adds an anti-fabrication rule to quote verbatim, not round, estimate, or recall from training data. It also exposes the re-call behavior for repeat questions. It does not discuss side effects, but this is an analysis tool and none are implied.

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 core purpose is front-loaded and the anti-fabrication warning is placed close behind it, so the most important selection info appears first. The only waste is the slight redundancy between 'All eight chapters return verified numbers' and the longer ANTI-FABRICATION sentence.

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 one-parameter tool with a descriptive schema and no output schema, the description gives the response contents and post-call behavior, which is mostly sufficient. But it says 'All eight chapters' while the schema enumerates ten valid chapters. The schema also claims format bs<1-5> while only bs1-4 plus two cmp- values are present. That inconsistency leaves the agent slightly unsure about the full valid scope.

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%, so the chapter parameter's enum, default, and format are already fully documented. The description only refers to 'the selected chapter' and 'all eight chapters', adding little beyond the schema.

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 action and object: 'Single Run bottleneck analysis for the selected chapter' and lists the exact metrics returned (availability, downtime split, throughput, OEE). It is clear about what find_bottleneck does, though it does not explicitly differentiate it from sibling tools such as compare_chapters or run_gain_loss.

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 establishes that the tool targets one selected chapter and instructs users to re-call it for follow-ups on the same chapter, so the context of use is implied. However, it never states when not to use it or mentions an alternative sibling, leaving routing guidance to inference.

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