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

Annotations only assert the mutation profile (readOnlyHint=false, destructiveHint=false, non-idempotent), which is actually somewhat under-informative for a tool with delete/remove actions. The description compensates with concrete behavior: anchored edits are all-or-nothing and name the failing index, a stale expected_version triggers CONFLICT with nothing written, and the full-text path can demand confirm_replace past 2000 characters. It stops short of describing exactly what assign/remove or delete do to already-assigned agents.

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 the verb list, then progressive disclosure through the preferred edit flow and the error taxonomy. The 'Raises:' block is useful but slightly verbose relative to the rest, and the multi-line prologue costs a little density.

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 13-parameter, 7-action tool with an output schema and rich annotations, the description covers the concurrency contract, the destructive-write guard, the error surface, and the recommended workflow. An agent could call this correctly on the first attempt without opening the schema for anything except the edit sub-fields, which the schema already documents.

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 already 100%, so the schema documents every parameter including the nested edit shape. The description still adds semantics the schema can't: the get→update→expected_version loop, the preference for instructions_edits over instructions, and the meaning of CONFLICT. It doesn't add much beyond the schema for the simpler action-scoped parameters, which caps it below 5.

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 opens with an explicit enumeration of the CRUD-plus-assign verb set and the resource ('personality traits'), which is specific and distinguishable from siblings like gnosari_manage_instructions and gnosari_manage_knowledge. It also explains what a trait actually is ('shape how an agent communicates'), which no structured field conveys.

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?

It gives an explicit workflow (get → update with expected_version), names the preferred action for changing existing instructions (update with instructions_edits rather than whole instructions), and states the condition for the fallback ('Pass whole instructions only to write a completely new set'). That is when-to-use plus when-not, which is rare.

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