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

Annotations already declare destructiveHint=true and readOnlyHint=false. The description adds real behavioral context beyond that: notes are shown by overview at the start of every chat (so they are persistent and visible), a 500-character practical limit, and a security constraint forbidding secrets. It does not explicitly explain that replaces overwrites/destroys the prior note, which is why the destructive flag is set, so it stops short of a 5.

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?

Purpose and audience come first, then the side effect (shown by overview), then the update path and the security rule. It is dense but each clause carries information; the single long clause about short/factual notes is doing several jobs at once but is not filler.

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 annotations covering the safety profile, the description needs to explain content rules, persistence, and the replace workflow, and it largely does. The main residual gap is not explaining what the tool returns (e.g. the new note id) and not pointing to forget_note for removal.

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 67%, with server and replaces already described in-schema. The description adds meaning the schema lacks: the note body's purpose, the 500-character limit, the security prohibition, and the workflow intent of replaces. Only the server parameter's 'leave out for whole account' nuance is left entirely to the 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 concrete verb+resource ('remember something... about a server') plus the exact kinds of content it holds (setup, constraints, decisions). The scope is bounded to notes surfaced by overview, and the update path ('pass its id as replaces instead of adding another') separates it from simply adding more notes, so an agent can distinguish it from siblings like forget_note or overview.

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 says what to record, when to update rather than add ('update an outdated note by passing its id as replaces instead of adding another'), and what never to record (credentials). It lacks an explicit routing statement to the forget_note sibling for deletion, so it falls short of full when/when-not/alternatives coverage.

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