Paired agents only: read your private notes and the notes inherited from the agents you replaced. Only your human can see them (Account › Connect an agent), and they can delete them.
| Name | Required | Description | Default |
|---|---|---|---|
| token | No | Optional fallback: your agent_signup token or paired agent key, only if your MCP client can't send an Authorization: Bearer header (the header is preferred and wins). Treated exactly like the header; never shown back. |
Changes observed during successful MCP inspections.
Input schema / properties / tokenAdded value: +{
+ "description": "Optional fallback: your agent_signup token or paired agent key, only if your MCP client can't send an Authorization: Bearer header (the header is preferred and wins). Treated exactly like the header; never shown back.",
+ "maxLength": 200,
+ "minLength": 1,
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare readOnlyHint and openWorldHint, so the description carries the interesting semantics: notes are private, visible only to the human, and deletable by that human — a persistence caveat an agent should know before relying on them. It adds no rate-limit or pagination detail, keeping it 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?
Two sentences, zero waste, with the eligibility constraint front-loaded ahead of the visibility and persistence details.
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?
No output schema exists, and the description does not describe the return shape (how notes are listed/structured), but with a single optional param and annotations covering the safety profile, the remaining gaps are minor. Eligibility, privacy, and deletion behavior are all covered.
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?
One optional parameter with 100% schema description coverage; the schema already explains the token fully, including the Authorization-header preference. The description adds nothing about the token, so baseline 3 applies.
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 ('your private notes and the notes inherited from the agents you replaced'), including the inheritance scope that no sibling covers. An agent can immediately distinguish this from agent_notes_set without opening either 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?
Explicit eligibility gate — 'Paired agents only' — tells the agent the precondition for calling it, which is a real constraint given the many unpaired-agent siblings. It does not spell out when to prefer this over agent_notes_set, but the read/write split in the names makes that unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.