eda-agent

Overview Schema Source Related Servers Discussions Admin

tool_catalog

Discover and filter 350+ EDA tools by category, maturity, or interaction to locate the right one without loading all schemas, then fetch its parameters.

Instructions

Discover tools by category / maturity / interaction without loading every schema.

The surface has 350+ tools; loading them all strains a client's context. This meta-tool returns a filtered, classified index so a client can find the right tool first, then rely on its full schema.

Filters (all optional, AND-combined): category: core, application, project, library, generic, schematic, pcb, audit, design, simulation, routing, meta, parts (and kicad on the KiCad backend; the EasyEDA tools file under the same subject headings as Altium's, so "pcb" means the same thing on either). "core" holds the EDA-agnostic main flow (review_design, get_board_info, list_components, list_nets, run_drc, run_erc) and is the usual starting point. Call with NO filter to get the live categories map rather than trusting this list. maturity: how far a tool can be exercised without Altium. offline needs no Altium at all; simulator is bridge-backed but every command it sends is implemented by the in-repo Altium simulator; live_only sends at least one command only real Altium answers. Filter on offline to find what runs with nothing open. interaction: readonly | silent | modal | partial. modal tools pop a blocking Altium dialog; partial ones leave the job incomplete: plan around both. query: case-insensitive substring over the tool name (and description when with_description). with_description: include the one-line summary per tool. with_schema: include each tool's parameters and required list. ESSENTIAL under the minimal toolset: no tool schema is loaded up front there, so calling tool_invoke without this means guessing argument names. Filter first, schemas are dropped past a cap so this cannot flood the very context the minimal toolset exists to protect.

Returns {count, tools:[{name, category, maturity, interaction [, description][, parameters, required]}], categories:{cat: n}}.

Input Schema

Name	Required	Description	Default
`query`	No
`category`	No
`maturity`	No
`interaction`	No
`with_schema`	No
`with_description`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.6.1Oct 29, 2026

TDQS

A4.9/5.0

Behavior5/5

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

No annotations are provided, so the description carries full burden and does so richly: it discloses the return shape, that filters are AND-combined, that schemas are dropped past a cap (a behavioral safety detail), and what each maturity/interaction value implies operationally (modal pops a blocking dialog, partial leaves jobs incomplete). This is exactly the beyond-schema context an agent needs.

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?

Front-loaded with purpose before the filter breakdown, and the per-filter bullets are well organized. It is somewhat long and the KiCad/EasyEDA parenthetical under category is rambling, but the length is largely justified by six undocumented parameters.

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?

Although an output schema exists (so return details are technically optional), the description still explains the return shape and, more importantly, the cap-on-schemas behavior and the minimal-toolset interaction that an agent must know to call it correctly. Nothing essential is missing.

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

Parameters5/5

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

Schema coverage is 0%, so the description must compensate fully and does: it defines each filter's semantics and enum values (category list, maturity offline/simulator/live_only, interaction readonly/silent/modal/partial), explains query as case-insensitive substring over name (and description when with_description), and clarifies with_description and with_schema behavior.

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 — 'Discover tools by category / maturity / interaction' — and frames its role precisely as a meta-tool that avoids loading 350+ schemas. An agent can immediately tell it apart from the concrete sibling tools like tool_invoke or tool_guide.

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

Usage Guidelines5/5

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

Explicitly gives the when-to-use rationale (context strain), the recommended starting point ('core' is the usual starting point), the discovery pattern (filter first, then rely on full schema / tool_invoke), and the special rule for with_schema under the minimal toolset. It even says to call with NO filter to get the live categories map rather than trusting the list.

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

Deploy Server