Skip to main content
Glama

site_notes

Read or append persistent notes about a website so future sessions and other agents remember how it works, where things are, and known gotchas.

Instructions

Read or write notes about a site that persist for future sessions and other agents: how things work, where things are, gotchas. Without text it reads them.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "site": "<site>"
    },
    "name": "site_notes"
  }
}

Input Schema

NameRequiredDescriptionDefault
siteYes
textNo
appendNoAdd to the notes instead of replacing them.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden. It does usefully disclose the durability trait (survives across sessions and agents) and the read/write mode switch based on the presence of text, but it omits what a read returns when no notes exist, whether replacing destroys prior content, and any permission or scope constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single compact sentence with a colon-delimited exemplar list, followed by a short mode-switching clause. It is front-loaded and every phrase carries information; the only minor weakness is that the exemplar list slightly crowds out guidance on the parameters.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 3 parameters, no annotations, and no output schema, the definition needs to stand on its own and mostly does for behavior, but it never explains the 'site' identifier format or what a read produces. For a persistence tool whose value depends on scoping notes to the right site, that is a meaningful omission.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33%: 'append' is documented in the schema, while 'site' and 'text' are not. The description compensates for 'text' by explaining that omitting it triggers a read, but leaves 'site' unexplained — it is unclear whether this is a URL, domain, hostname, or active-tab identifier, which is the most critical parameter to get right.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a concrete resource (notes about a site) and both modes (read/write), plus the distinguishing trait that notes persist for future sessions and other agents. It also clarifies the ambiguous dual mode with 'Without text it reads them.' It does not explicitly distinguish itself from sibling tools, but the persistence framing is specific enough to separate it from per-session tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a clear use rationale — recording 'how things work, where things are, gotchas' for later sessions and other agents — which implies when to reach for it. However, there is no explicit when-not guidance and no named alternative for ephemeral or in-session memory needs, leaving the agent to infer boundaries.

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