Knowledge Base

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

The description goes beyond the destructiveHint annotation by explicitly warning that delete is destructive and cannot be undone, and that a lost encryption key makes the store unrecoverable. It also discloses that ingest can save to kb/disk/both and that encryption operations generate or rekey keys, making side effects clear.

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 dense but well organized: it opens with the core purpose, lists operations, gives usage direction, states destructive consequences, and summarizes parameter/response behavior in a compact set of sentences. Each sentence contributes distinct information without redundancy or 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?

Despite having no output schema, the description specifies the response envelope as [OK] or [ERROR] and details what each action returns: search/list/get return entries, stats returns counts, and delete reports chunks removed. It also covers important behavioral context like key file handling and default behaviors, making the tool fully actionable.

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?

Although the schema already has 100% parameter description coverage, the tool description adds valuable cross-parameter semantics: it maps each action to its relevant parameters, explains that save_to defaults to 'kb' and max_results to 8, notes that last_updated is auto-detected from fetched URLs, and warns that key_file must only be a path, never the secret itself.

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 clearly states the tool manages the local knowledge base and enumerates specific operations: search, ingest, list, get, delete, stats, and encryption. It explicitly contrasts with sibling tools by saying do NOT use for fresh external search or fetching a new page, naming infobroker_search_web and infobroker_fetch_page.

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 explicit when-to-use guidance: archive a generated report with source_type 'report' and save_to 'kb', revisit stored content, or manage encryption keys. It also explicitly states when not to use the tool and points to the appropriate sibling tools, leaving no ambiguity about selection.

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