Skip to main content
Glama

Jonas Splinter (jsplinter.nl)

Search updates

search_updates
Read-onlyIdempotent

Search the dated updates Jonas posts about what he is building. Matches any of the words in title, text, project and tags and ranks by how many match; without a query it returns the newest. Optional filters: project, tag, since. Each result has the full text (updates are short), tags and a URL; use get_update for one update by slug.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_updates"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagNoOptional tag key as returned by list_tags, e.g. "claude-code".
limitNoMaximum number of results (1-25, default 10).
queryNoWords to look for, e.g. "astro rebuild" or "accessibility". Optional; leave out for the newest updates. Max 120 characters.
sinceNoOptional earliest date, YYYY-MM-DD, e.g. "2026-11-01".
projectNoOptional project filter: jsplinter, personal, blockspot, voucheralarm, automateandtweak, games. ("jsplinter" = the site itself, "personal" = personal notes.)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent, non-destructive and closed-world, so the description's job is to add retrieval semantics — and it does: matching is any-word across title/text/project/tags, ranked by match count, with recency as the fallback ordering. It also discloses that results carry full text because updates are short, which tells the agent it needn't re-fetch bodies.

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?

Three sentences, front-loaded with what is searched, then matching behavior, then filters, then result shape and the sibling hand-off. No sentence is redundant and nothing is buried at the end.

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

Completeness5/5

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

With no output schema, the description still describes the return payload (full text, tags, URL), and with zero required parameters it explains the no-query default. For a five-param read tool with full annotation coverage, nothing an agent needs to call it correctly is missing.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3, but the description adds meaning the schema lacks: it explains that query words match across title, text, project and tags rather than being a substring search, and that ranking is by number of matched words. It doesn't elaborate on limit or since beyond the schema, but the added matching semantics justify the bump.

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

Purpose5/5

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

States a specific verb and resource ("Search the dated updates Jonas posts") and scopes the corpus to "what he is building," which distinguishes it from post/project listing siblings. An agent knows exactly what this retrieves and over what body of content.

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?

Explicitly explains the query-less case ("without a query it returns the newest") and routes single-item lookups to get_update by slug. It names the optional filters but doesn't state when to prefer this over broader listing tools, so it stops just short of full when/when-not coverage.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources