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

Annotations already establish readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely useful behavior the annotations do not: the default is scoped to your own notes, other agents' notebooks are read-only, and the call can be retargeted to the workspace-wide corpus.

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 tight sentences with the core purpose front-loaded and the three search modes following in priority order; no filler. The final sentence is a fragment but remains readable and information-dense.

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 read-only, 6-parameter, fully schema-documented tool, the description covers purpose, default scope, and mode switching adequately. It does not describe the return shape (note keys/values, result ordering), which is a minor gap given there is no output schema.

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% and the schema already documents filter_agent_id, scope_ref_id, scope, and limit in comparable detail, so the description is largely consolidating rather than adding. It also writes filter_agent_id=<int> while the schema specifies a numeric string (e.g. "57"), a small mismatch that could mislead on type.

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+resource ('Full-text search in your notebook') and immediately clarifies scope behavior, so the agent knows it is a search/read tool. It does not, however, distinguish itself from close siblings such as notes_recall or notes_save, so the reader must infer the boundary from the name alone.

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 mode-selection guidance: default is own notes, filter_agent_id for another agent's notebook, 'all'/'*' for workspace-wide, and scope_ref_id for listing a person/thread. It never names an alternative tool (e.g. notes_recall) or states when not to use this one, so it stops short of full routing guidance.

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