Skip to main content
Glama

update_csp

Idempotent

Replace a contextual security policy's rules, priority, exceptions, or metadata. Supply complete rule objects to retain fields and check the CSP schema before adding restrictions or approvals.

Instructions

Update a contextual security policy. Supplied rules replace the whole object; include all fields to retain. Check zihin://schemas/csp_config because unknown fields may be accepted without effect. Use behavior.must_not_tools for tool restrictions and require_approval_for with approval_policy_id for native-chat human approval.

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": {
      "csp_id": "<csp_id>"
    },
    "name": "update_csp"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoNew name
rulesNoNew rules, replacing the previous rules completely
csp_idYesUUID of the CSP policy to update
priorityNoNew priority
exceptionsNoNew rule exceptions
descriptionNoNew description

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv2.2.4
    • changedInput schema / properties / csp_id / description
      Previous value: -"UUID da CSP a atualizar"New value: +"UUID of the CSP policy to update"
    • changedInput schema / properties / description / description
      Previous value: -"Nova descrição"New value: +"New description"
    • changedInput schema / properties / exceptions / description
      Previous value: -"Novas exceções"New value: +"New rule exceptions"
    • changedInput schema / properties / name / description
      Previous value: -"Novo nome"New value: +"New name"
    • changedInput schema / properties / priority / description
      Previous value: -"Nova prioridade"New value: +"New priority"
    • changedInput schema / properties / rules / description
      Previous value: -"Novas regras (substituem as anteriores por completo)"New value: +"New rules, replacing the previous rules completely"
  2. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=true, so the safety profile is covered. The description adds behavior beyond that: full-replacement semantics with silent loss of omitted rule fields, and the warning that unknown fields may be accepted without effect — a silent no-op trap the annotations do not reveal. It does not describe the response or error behavior for an invalid csp_id.

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?

Three dense sentences, front-loaded with the action and immediately followed by the highest-risk caveat (replacement). Every sentence carries information; the jargon-dense schema pointer and field names cost some readability but no filler is present.

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?

For a mutation tool with nested objects and no output schema, the description covers the main hazards: replacement semantics, unknown-field acceptance, and the nesting used for tool restrictions and approvals. It omits confirmation of what is returned and how failures (e.g. unknown csp_id, invalid rules) are surfaced, which an agent might need.

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 coverage is 100%, so the six top-level parameters are already documented and the baseline is 3. The description adds genuine meaning for the untyped nested 'rules' object by naming behavior.must_not_tools, require_approval_for and approval_policy_id, though it does not explain the shape or semantics of those fields or how they interact.

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

Purpose4/5

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

The first sentence names a specific verb ('Update') and resource ('contextual security policy'), which is enough for an agent to distinguish it from create_csp/delete_csp/get_csp. It stops short of explicitly naming a sibling or its scope boundary (e.g. whole-policy vs. toggle), so it is clear but not differentiating.

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?

It gives concrete operational guidance the caller needs before invoking: rules replace the whole object, so all fields must be supplied to retain them, and a schema resource is provided for validation. It does not state when to prefer toggle_csp or create_csp instead of a full update, so the selection guidance is contextual rather than explicit.

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

Deploy Server

Other Tools