NEMAD MCP

nemad_read_results

Read-onlyIdempotent

Read paginated cached search results by cache key, returning up to 100 results per page and supporting continuation with start and end indexes.

Instructions

Read a cached page: start inclusive, end exclusive, at most 100 results.

Omit end_index for the next 100 results. An empty search produces an empty page. Results are local to this process and expire after 15 minutes.

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": {
      "cache_key": "<cache_key>"
    },
    "name": "nemad_read_results"
  }
}

Input Schema

Name	Required	Description	Default
`cache_key`	Yes
`end_index`	No
`start_index`	No

Output Schema

Name	Required	Description	Default
`results`	Yes
`cache_key`	Yes
`end_index`	Yes
`start_index`	Yes
`total_count`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Nov 9, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds substantive behavior on top: a hard 100-result page cap, the 15-minute expiry, process-local scope, and the empty-page case. What is missing is the failure mode for an expired or unknown cache_key, which matters given the stated expiry.

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?

Four short sentences with zero filler; the core paging contract (inclusive start, exclusive end, 100 max) is front-loaded and the constraints follow in descending order of importance. Nothing repeats the annotations or the schema.

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?

For a three-parameter paging tool with an output schema that handles return values, the description covers page sizing, boundary conventions, lifetime, and scope. It is still incomplete on the required cache_key's provenance and on what happens when the cache has expired or the requested range exceeds cached results.

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 0%, so the description must carry the parameters, and it does clarify start/end semantics (start inclusive, end exclusive) and the null end_index default. However, the required parameter cache_key is never explained — no indication that it is the handle returned by a prior search — leaving the most important input undocumented in both schema and description.

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?

States a specific verb and resource — 'Read a cached page' — and immediately defines the paging semantics, so an agent knows this retrieves a slice of previously cached results. It does not mention where the cache_key originates (e.g., which sibling search produces it), so differentiation from nemad_search / nemad_list_cache is left implicit.

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?

Gives one concrete usage rule — 'Omit end_index for the next 100 results' — which is real guidance for pagination, plus the caveat about process locality and 15-minute expiry. It never states when an agent should call this rather than re-running nemad_search or checking nemad_list_cache, and the prerequisite (a prior search that populated the cache) is only inferable.

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

Deploy Server