Extract engagement material from a document

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

With no annotations provided, the description fully carries the behavioral burden and does so well. It discloses that the tool performs mechanical keyword and sentence-ending scanning, does not read or understand the document, is lossy, writes nothing, and returns output with source line numbers and register-ready JSON. It also warns that pasting already-read text will not improve accuracy, which is valuable behavioral context beyond the schema.

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 core operation and the no-write guarantee, followed by a clearly emphasized limitation and three concrete use cases. Although it is bilingual and somewhat long, the repetition serves the tool's ja/en audience, and every sentence adds either capability, limitation, or usage guidance. Nothing is 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?

For a tool with no output schema and no annotations, the description is remarkably complete. It tells the agent what the tool returns (Markdown table with source line numbers and update_engagement JSON), what it cannot do (understand the document), when to use it, when to avoid it, and how the parameters behave, including the path/text exclusivity and truncation reporting. The agent can decide correctly whether and how to invoke it.

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 is 3, and the schema already documents all six parameters. The description adds meaningful semantic context beyond the schema, especially for the text parameter: it warns that pasting already-understood text does not improve accuracy and clarifies that text is useful only for mechanical formatting into line-numbered tables and JSON. This goes beyond what the schema states.

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?

Describes a specific operation: mechanically extract engagement material candidates (risk, stakeholder, system, requirement, action) from a document and return a Markdown table with source line numbers plus JSON for update_engagement. The explicit statement that it does not read or understand the document sharply distinguishes it from sibling document tools like read_document, ingest_document, and summarize_document_for_architecture.

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?

Gives explicit when-to-use guidance: it is appropriate only for (1) scanning files too large for the conversation, (2) recording skipped lines and reasons, and (3) producing register-ready JSON with citations. It also explicitly says when not to use it: if the agent can already read the full text, the agent should do candidate selection itself because this tool is a lossy inferior version.

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