Escape hatch: chamada OData crua. method (GET/POST/PATCH/PUT/DELETE) + path (ex.: "/Litigations/2479") + query/body opcionais. Cobre endpoints/ações fora das tools nomeadas.
| Name | Required | Description | Default |
|---|---|---|---|
| body | No | ||
| path | Yes | ||
| query | No | ||
| method | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are all false/unknown, so the description carries the full transparency burden. It reveals that arbitrary HTTP methods including DELETE/POST/PATCH/PUT are accepted, but it does not warn about potential side effects, authentication requirements, or raw response/error behavior. The 'raw OData call' label gives some signal, but not enough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is only two sentences, front-loaded with the key 'Escape hatch' concept, and contains no fluff or repetition of schema properties.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a deliberately open-ended raw OData tool, the description adequately covers purpose, method, path, and optional inputs. However, with no output schema, it gives no guidance on response format, pagination, or error behavior, and it does not mention authentication prerequisites even though sibling tools like authenticate/connect exist.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 0% description coverage, so the description must add meaning. It compensates by explaining the method enum, giving a concrete path example ('/Litigations/2479'), and noting that query/body are optional. It does not detail OData query syntax, but this is acceptable for a generic escape-hatch tool.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the tool as an 'escape hatch' for raw OData calls and specifies the core inputs (method, path, query/body). It also distinguishes itself from siblings by explicitly covering endpoints/actions outside the named tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'Cobre endpoints/ações fora das tools nomeadas' gives clear guidance that this tool is for cases not covered by the dedicated sibling tools. It implies use only when no named tool fits, though it does not explicitly list when-not-to-use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The core legalone_get/list/create/update tools are clearly separated by entity and verb, so common lookups are easy to pick. However, legalone_odata_get and legalone_request duplicate the named CRUD surface, lawsuits vs litigations are near-synonyms in a legal context, and connect/toolkit_info/authenticate have overlapping connection/status duties. Descriptions help resolve most cases, but several tool pairs could still be misselected.
The majority of tools follow a consistent legalone_<verb>_<entity> pattern, which is good. But auxiliary tools break the pattern: legalone_customfield_options, legalone_odata_get, legalone_request, legalone_metadata, authenticate, connect, marketplace, report_bug, show_version, and toolkit_info use bare verbs, nouns, or platform-infrastructure names. The result is mixed conventions that remain readable but are not consistent across the whole set.
With 45 tools, this set is well beyond the 3–15 well-scoped range and above the 25-tool threshold for too many. Many tools are repetitive CRUD variants per entity, plus several infrastructure and marketplace tools that inflate the agent's selection space. A smaller entity-focused set plus one generic OData escape hatch would have covered virtually the same functionality.
Core legal entities like lawsuits, litigations, contacts, appointments, tasks, and updates have create/get/list/update coverage. However, documents, users, areas, service types, and custom field definitions lack named update/delete helpers, and no entity has a dedicated delete tool. The generic legalone_request/odata_get escape hatches fill these gaps, but the lifecycle coverage is uneven.