Burs-IA Utils

Revisar herramientas MCP

mcp-tools-lint

Read-onlyIdempotent

Revisa definiciones de herramientas MCP: nombres, descripciones, inputSchema, requeridos y propiedades sin documentar; devuelve un puntaje 0-100. Cuándo: hay que leer, convertir o revisar una descripción de agente, una lista de herramientas, un documento OpenAPI o un recibo según el formato de su protocolo. No para: revisar una Agent Card de A2A según la especificación A2A (agent-card-validate). Efectos secundarios: ninguno (solo lectura, sin red, sin estado guardado). Determinista: la misma entrada da la misma salida. Límites: entrada JSON de hasta 64 KB, 1 s por llamada, resultado de hasta 1 MB.

EN: Lints MCP tool definitions (a tools/list result or array): name syntax and uniqueness, description presence/length, inputSchema root type, required keys defined in properties, undocumented properties, and annotation hints; returns a 0-100 score. [EN completo / full EN: inputSchema.description]

Input Schema

Name	Required	Description	Default
`tools`	Yes	Array of tools or an object with a tools array (array or object; required).

Output Schema

Name	Required	Description	Default
`score`	No
`tools`	No
`errors`	No
`issues`	No
`warnings`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 2, 2026

addedInput schema / properties / tools / examples

Added value: +[
+  {
+    "tools": [
+      {
+        "inputSchema": {
+          "properties": {
+            "q": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "x"
+          ],
+          "type": "object"
+        },
+        "name": "bad name"
+      }
+    ]
+  }
+]

Changed1 schema field changedNov 1, 2026

addedInput schema / description

Added value: +"EN: Lints MCP tool definitions (a tools/list result or array): name syntax and uniqueness, description presence/length, inputSchema root type, required keys defined in properties, undocumented properties, and annotation hints; returns a 0-100 score. When: an agent description, tool list, OpenAPI document or receipt has to be read, converted or checked against its protocol format. Not for: checking an A2A Agent Card against the A2A specification (agent-card-validate). Side effects: none (read-only, no network access, no stored state). Deterministic: the same input gives the same output. Limits: JSON input up to 64 KB, 1 s per call, result up to 1 MB."

First observedNov 1, 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/no-open-world, so the 'solo lectura, sin red, sin estado guardado' sentence mostly restates them. But the description adds genuinely non-structured traits: determinism and hard limits (64 KB input, 1 s per call, 1 MB result), which an agent cannot infer from the schema or annotations. It does not say whether the score is accompanied by per-finding details (though an output schema exists).

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, then When/Not-for/Side-effects/Determinism/Limits in a scannable order — no hunting required. The main inefficiency is the verbatim duplication of the full EN text that also appears inside inputSchema.description, plus the loosely related OpenAPI/receipt examples in the 'Cuándo' list.

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?

An output schema exists so return values need no explanation, annotations carry the safety profile, and the schema fully documents the one parameter. The description still covers the non-structured gaps that matter for correct invocation: accepted input shapes, size/time limits, determinism and the nearest non-overlapping sibling.

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% and the single 'tools' parameter already documents both accepted shapes ('array or object') with a worked example. The description's 'a tools/list result or array' adds no detail beyond that, so 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 ('Revisa definiciones de herramientas MCP') and enumerates exactly what is checked: name syntax/uniqueness, description presence, inputSchema root type, required-vs-properties, undocumented properties, annotation hints, plus the 0-100 score output. The explicit 'No para: ... (agent-card-validate)' clause distinguishes it from at least one sibling by name.

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?

An explicit 'Cuándo' clause and an explicit exclusion ('No para' → agent-card-validate) give real routing guidance. However, the 'Cuándo' text is broad and partly off-topic (OpenAPI documents, 'recibos'), and it never mentions the far more likely alternatives in this sibling list — mcp-server-json-lint, tool-definition-convert, mcp-protocol-compat — so the most probable confusion is left unaddressed.

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

All Burs-IA Utils tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?