Tailor the ADM

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

With no annotations, the description carries the full burden, and it discloses the key behaviors: it returns a table (表で返す), specifies what the table contains, and states the central design premise that phases get cut rather than run in full. The '返す / return' phrasing implies a non-persisting design operation. It does not explicitly address side effects or edge cases like an undersized timebox, but the core behavior is transparent for a design-and-return tool.

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 description is compact: the first sentence front-loads the action and the full output specification, and the second adds the philosophical premise. The bilingual Japanese/English duplication doubles the length, but this is justified by the lang parameter supporting ja, en, and both. Every part earns its place with no filler.

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?

Since there is no output schema, the description properly takes on the job of explaining the return value: a table containing phases to run/cut, deliverables, durations, and review placements. It covers the primary inputs (scale, purpose, timebox) and the design logic. Minor gaps remain — it does not address what happens when timeboxWeeks is absent or how hasExistingEa influences the result — but the schema covers those parameters, so the overall picture is complete enough.

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 100%, so the baseline of 3 applies. The description echoes scale, purpose, and timebox as the three design inputs but adds no new parameter-level meaning beyond what the schema already documents — the cutting behavior is stated in both the timeboxWeeks schema description and the tool description. The lang and hasExistingEa parameters are omitted from the description but fully covered in 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 states a specific verb and resource — 'Design a tailored ADM from scale, purpose, and timebox' — and enumerates the concrete outputs: phases to run/cut with reasons, deliverables to produce/skip, durations per phase, and review placements. This clearly distinguishes it from siblings like compare_with_togaf, diagram_adm_cycle, and map_security_to_adm, which do comparison, diagramming, and security mapping respectively.

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 provides a clear trigger context: use this when you have a scale, purpose, and timebox and want a custom, cut-down ADM plan rather than the full framework. The premise statement ('ADM is meant to be cut down, not run whole') further clarifies the intended use case. It does not explicitly name alternatives or when-not-to-use, but the positioning against comparison/diagramming siblings is reasonably clear.

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