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

Annotations only say readOnlyHint=false and openWorldHint=false. The description goes well beyond them: asynchronous ingest pipeline (parse → structure-aware chunk → embed with the KB's bound key), hash-based de-duplication where re-adding is a no-op surfaced via the `deduped` flag, and the embedding-key precondition. This is exactly the extra behavioral context annotations cannot carry.

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?

Front-loaded with purpose and the primary disambiguation, and nearly every sentence carries a distinct fact (alternative tool, file path, async pipeline, dedup, prerequisite). Slight redundancy between the opening clause and 'Add a text document…' keeps it just short of 5.

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 an output schema already present, the description fills in what the structured fields do not: the async ingest model, dedup semantics and its response flag, the embedding-key precondition, and the file-vs-text boundary. Nothing needed to call it correctly is missing.

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 schema already documents text (plain text, max 1 MB), kb_id (from findagent_list_kbs), and the optional title default. The description adds no syntax or format detail beyond the schema, so the baseline of 3 applies.

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?

States a specific verb and resource ('Puts CONTENT INTO a knowledge base' / 'Add a text document'), and explicitly names the sibling it is not — findagent_attach_kb — plus the file-upload path. An agent can distinguish this from attach_kb and the uploader without opening any schema.

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?

Explicitly covers when-not-to-use (findagent_attach_kb for reachability; web uploader for PDF/markdown/docx) and states the hard prerequisite that the KB must have an embedding key bound or ingest fails. This is a complete routing decision.

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