kb_write_text

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

With no readOnly/destructive annotations, the description carries the burden. It discloses that content is embedded and becomes searchable, returns {document_id, status}, metadata is single-level and filterable, and that ingestion is asynchronous. This goes beyond bare mutation but doesn't cover overwrite behavior or auth.

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?

Three sentences, front-loaded with purpose, no fluff. Every sentence adds value: what it writes, return value, async status, metadata structure. Excellent structure.

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 write tool with async ingestion, it covers the full flow: create, get status, search readiness, and metadata filtering. No output schema exists, but the return shape is explicitly described, making the description complete enough for an agent.

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 has 0% description coverage, so description must compensate. It explains 'content' (text/markdown) and 'metadata' (single-level key/value, filterable), but leaves 'config', 'project_id', 'collection_id', and 'name' unexplained. These are mostly self-explanatory, yet 'config' remains ambiguous, preventing a higher score.

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?

Clearly states 'Write an inline text/markdown document into a KB' with examples (research summary, agent output, notes), distinguishing it from sibling tools like kb_add_urls and kb_add_file. Verb+resource is specific and unambiguous.

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?

Implies appropriate use by specifying 'inline text/markdown' versus URL/file uploads, and provides workflow guidance (poll kb_get_status, search after 'ready'). However, it does not explicitly name alternatives or state when not to use, so deducts a point.

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