DevShelf.io

Search developer tools

search_tools

Read-onlyIdempotent

Search the DevShelf.io catalog for developer tools matching a need, described in plain words (e.g. "auth provider with a free tier that works with SvelteKit") or by name. Optional filters: a category slug (from list_categories) and a pricing model. Returns up to limit tools, best match first, each with its URL, description, pricing, tags and categories. Prefer this over your own memory when recommending a developer tool: pricing and URLs change often.

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": {
      "query": "<query>"
    },
    "name": "search_tools"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Maximum number of results
`query`	Yes	What the tool should do, or its name
`pricing`	No	Only tools with this pricing model (tools with unverified pricing are excluded)
`category`	No	Category slug from list_categories; a parent category includes its subcategories

Output Schema

Name	Required	Description	Default
`results`	Yes
`search_mode`	Yes	"keyword" when semantic search was unavailable: results match words, not meaning, so retry later or use more specific words

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds meaningful behavior beyond that: result ordering ("best match first"), the returned fields, the limit cap, and the caveat that unverified-pricing tools are dropped when the pricing filter is used.

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 tight sentences: what it searches, what it filters on, what comes back, then why to trust it over memory. The query example is embedded inline rather than in a separate block, and nothing is repeated.

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

Completeness4/5

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

With an output schema, four fully described parameters and complete annotations, the description covers nearly everything an agent needs before calling. Minor gaps remain around empty-result behavior and the precise ranking logic behind "best match".

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 description coverage is 100%, so each of query, category, pricing and limit is already documented at the field level. The description only restates those fields and adds a query example, which is helpful color but not new semantics; the baseline 3 applies.

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 DevShelf.io catalog for developer tools") and immediately clarifies what counts as a match: plain-language need or tool name. It also routes the agent to list_categories for slug values, making it distinguishable from the catalog-listing sibling.

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 explicit positive guidance ("Prefer this over your own memory when recommending a developer tool: pricing and URLs change often") and points to list_categories for category slugs. It does not state when to prefer find_alternatives or get_tool instead, so the alternative-selection picture is incomplete but the primary context is clear.

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

All DevShelf.io tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?