Summarize a document from an architecture standpoint

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

With no annotations, the description carries the behavioral burden. It candidly discloses that the scan only inspects keywords and sentence endings, that it is worse than the client's own reading, and that the output is structured material with line numbers and missing-viewpoint follow-ups rather than a summary. Some details about the exact output format or viewpoint set are absent, but the key behavioral traits are clearly exposed.

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 front-loaded with the verb and resource, then the output shape, then the anti-goal. It is efficient and has no filler, though the Japanese and English sections mirror each other closely, adding some length. Still well-structured and readable.

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?

Given no output schema and no annotations, the description explains the core return value: matched excerpts with line numbers per viewpoint, plus guidance for uncovered viewpoints. It also documents the important text-input caveat. It is not exhaustive about the exact viewpoint taxonomy or response structure, but it gives an agent enough context to select and invoke the tool correctly.

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 baseline is 3. The description adds meaningful semantics beyond the schema by clarifying the two input modes (path vs text) and warning that text reuse does not boost accuracy. This elevates it above mere schema repetition.

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 action and resource: inventory a document against architecture viewpoints and return line-numbered excerpts per viewpoint. It also explicitly distinguishes itself from a prose summary ('要約そのものではなく / rather than a prose summary'), making it clearly different from sibling read/extract/ingest tools.

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 gives clear guidance on when to use path vs text, and explicitly warns that pasting already-read text will not improve accuracy and is only useful for mechanical formatting. It does not explicitly name sibling tools as alternatives, so it stops short of full when-not-to-use guidance.

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