Skip to main content
Glama

aws_knowledge_read

Read-onlyIdempotent

Retrieve the full text of an official AWS document when a search excerpt is insufficient, using only the returned URL and avoiding arbitrary URL fetches.

Instructions

Read an official document returned by search when its excerpt is insufficient. Fixed upstream; no arbitrary URL fetch.

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": {
      "url": "<url>"
    },
    "name": "aws_knowledge_read"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
maxLengthNo
startIndexNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.0
    • changedInput schema / required
      Previous value: -[
      -  "url",
      -  "startIndex",
      -  "maxLength"
      -]New value: +[
      +  "url"
      +]
  2. First observedv0.4.1

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds the genuinely useful behavioral fact that the target must originate upstream (no arbitrary URL fetch), which is more than the annotations say. It says nothing about truncation or chunking behavior for long documents, which the startIndex/maxLength parameters imply is real.

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

Conciseness5/5

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

Two short sentences, the primary use case front-loaded and the safety constraint immediately behind it. Nothing is redundant with the title or schema, and every clause carries information.

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?

There is no output schema, so the description should say what a successful read yields, but it does not. Combined with unexplained pagination parameters, an agent cannot tell whether one call returns the whole document or whether it must loop over startIndex, which is material for a tool whose whole purpose is fetching more content.

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

Parameters2/5

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

Schema description coverage is 0%, so the description carries the full burden and largely drops it: maxLength and startIndex go completely unexplained, leaving the agent to guess that reading is windowed/truncated. The one thing it does clarify is the provenance of url (must come from search results, not be fabricated), which is valuable but covers only one of three parameters.

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?

"Read an official document returned by search" names a specific verb and resource, and explicitly anchors the resource as the output of the aws_knowledge_search sibling, so an agent can tell the two apart without opening schemas. It stops short of 5 only because it never says what form the document comes back in (full page text, markdown, chunked window), which is the ambiguity an agent most needs resolved.

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

Usage Guidelines4/5

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

Gives a concrete trigger: use this when the search excerpt is insufficient, which is exactly the decision point an agent faces after aws_knowledge_search. It adds a negative constraint too ("no arbitrary URL fetch"), ruling out generic fetch behavior, but offers no guidance on when the excerpt is enough or how to decide to escalate.

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