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

Annotations only declare readOnlyHint=false and openWorldHint=false, but the description adds substantial behavior: the authorization requirement for org targets, that org KBs are auto-available to every agent/department run for active members, what each mode actually does at runtime, and that attachments are not part of the agent manifest so updates need no re-publish. This is context an agent cannot get from the annotations.

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-loads the core action and the add_kb_document contrast, then handles targets, mode, and the manifest detail in a logical order. Slightly long, but nearly every sentence carries distinct operational value rather than padding.

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?

An output schema exists, so return values need not be described, and the definition still covers authorization, target identification, mode semantics, and a non-obvious deployment caveat. Sufficient for an agent to invoke it 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, but the description adds real meaning: it explains what each mode value does operationally (tool grants a search_knowledge tool, auto_inject prepends passages), recommends target_slug over target_id, and clarifies omission of target fields for user_personal. This goes beyond the terse enum labels.

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 (connects/attaches) and resource (an EXISTING knowledge base) and explicitly scopes it against the sibling findagent_add_kb_document, which handles content addition. An agent can differentiate this from add_kb_document without opening either 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?

Gives concrete when-to-use conditions: attach a KB you own to an agent/department you own, to an org you administer, or as a personal KB. Names the exact lookup tools for each target type (findagent_list_my_agents, findagent_list_orgs) and states the auth requirement (org owner/admin). Nothing is left to inference.

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