recall

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

No annotations, so the description carries the burden and does so reasonably: 'Read' implies non-mutating, the turn-availability restriction is disclosed, and the redundancy with finish_turn output is surfaced. It stops short of describing pagination/ordering beyond 'newest N' or what happens with an empty notebook.

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?

Dense but front-loaded: purpose and return shape come first, then filtering, then the timing caveat. The semicolon-chained clauses are slightly awkward but nothing is wasted.

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?

With no output schema and no annotations, the description supplies return contents (id, turn written, tag), defaults, filtering behavior, and a usage constraint. Adequate for a 2-param read tool, though edge behavior (empty result, ordering beyond 'newest') is unstated.

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 0%, so the description must compensate, and it does: it explains `tag` acts as a filter and that `limit` returns the newest N with a default of 50. Both parameters get meaning beyond the bare schema.

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 (read) and resource (notebook/notes), and cross-references the sibling `remember` that creates those notes. An agent can distinguish it from remember/forget without opening a 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 an explicit timing condition ('Usable while it is not my turn') and notes that the last few notes already arrive with each finish_turn result, implicitly telling the agent when a call may be unnecessary. No explicit when-not or named alternatives (e.g. forget) beyond that.

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