Chat notes

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

Annotations already declare openWorldHint=true, readOnlyHint=false and destructiveHint=false; the description adds real context by saying notes are shared across every agent and the user, which tells the agent writes are globally visible and persistent. It does not explain what action=delete actually removes or whether it is reversible, and the delete action sits uneasily with destructiveHint=false without any clarification. That gap keeps it at a 3 rather than higher.

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 sharing scope are front-loaded in the first clause, followed by concrete content examples, with the cross-reference to tg_resolve_chat last. The telegraphic 'action=get|set|append|delete|list' is compact and readable. No sentence is wasted, though the fragment style is terse at the cost of some connective clarity.

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 4-parameter mutation-capable tool with no output schema and only 50% parameter documentation, the description covers purpose and sharing semantics but leaves the return value, per-action parameter requirements, and delete consequences unspecified. It is adequate to pick the tool but not fully sufficient to invoke every action 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 50%: chat and account have descriptions, text and action do not. The description compensates partially by enumerating the action values, but it never states which operations require the 'text' parameter or that 'chat' is unnecessary for action=list. Baseline 3 is appropriate given the schema does half the work.

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?

Names a specific resource (shared, persistent per-chat notes) and enumerates the operations via action=get|set|append|delete|list, so an agent knows exactly what this tool manages. The parenthetical examples ('where passwords are posted, which channel holds the files') make the scope concrete. It does not explicitly contrast itself with sibling tools, which keeps it from a 5.

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?

The description implies when the tool is worth using by giving example note content (naming patterns, password locations, file channels) and by noting 'tg_resolve_chat returns the note too', suggesting an agent already resolving a chat need not call action=get. However, it states no explicit when-to-use/when-not rule, no prerequisite that chat is needed for get/set/append/delete but not list, and no alternative named for note-like storage.

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