Skip to main content
Glama
CorgiCorner

Bisibility

by CorgiCorner
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Update project defaults

update_project_defaults

Confirm a reviewed preview to update a Bisibility project's default rank-check schedule, SERP depth, and SERP market, ensuring stale drafts are rejected.

Instructions

Confirm a preview_project_defaults draft using its exact source hash, revision, token and stable command key in review (confirmed:true). Missing review is refused by current servers; stale/expired review requires a new preview. Never auto-confirm. Update the project default rank-check schedule, SERP depth, and SERP market. The schedule is replaced as a whole: omitted schedule fields (frequency, cron_expression, jitter_minutes, timezone) reset to their defaults (jitter 60, timezone UTC, no cron). serp_depth and serp_stop_on_match are independent of the schedule and keep their stored values when omitted. Provide country and device together, or a location_key, to move the default SERP market. Use search_locations and pass its location_key verbatim to preserve the exact location-language pair.

Input Schema

NameRequiredDescriptionDefault
cityNo
deviceNoDevice whose search or ranking data is being selected.
reviewNo
countryNo
timezoneNo
frequencyYesSchedule frequency that determines when rank checks run.
project_idYesIdentifier of the bisibility project to operate on; list_projects returns valid project ids.
serp_depthNoDefault number of SERP results to scan per rank check (10, 20, 50, or 100). Omitted keeps the stored depth.
location_keyNoCanonical country, region, or city key. Append @language for a non-default language pair; an unqualified key uses the country's default language.
jitter_minutesNo
cron_expressionNoCron expression used when frequency is custom_cron; otherwise null.
idempotency_keyNo
serp_stop_on_matchNoSet false to fetch the full configured depth for competitor snapshots.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.17.1
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / location_key / description
      Added value: +"Canonical country, region, or city key. Append @language for a non-default language pair; an unqualified key uses the country's default language."
    • changedInput schema / properties / location_key / pattern
      Previous value: -"^[A-Z]{2}(\\/[^/]{1,80}){0,2}$"New value: +"^[A-Z]{2}(\\/[^/@]{1,80}){0,2}(@[a-z]{2,3}(-[a-z0-9]{2,8})?)?$"
    • addedInput schema / properties / review
      Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "confirmed": {
+      "const": true,
+      "description": "True only after the caller explicitly approves the displayed draft and impact.",
+      "type": "boolean"
+    },
+    "expected_revision": {
+      "description": "Opaque decimal revision string from preview; never convert to a number.",
+      "pattern": "^(0|[1-9][0-9]*)$",
+      "type": "string"
+    },
+    "expected_source_hash": {
+      "description": "Exact source hash returned by the reviewed preview.",
+      "pattern": "^[a-f0-9]{64}$",
+      "type": "string"
+    },
+    "idempotency_key": {
+      "description": "Stable command key; reuse with the exact body after a lost response.",
+      "maxLength": 128,
+      "minLength": 8,
+      "type": "string"
+    },
+    "preview_token": {
+      "description": "Unmodified issuer-bound preview token.",
+      "maxLength": 8192,
+      "minLength": 1,
+      "type": "string"
+    }
+  },
+  "required": [
+    "expected_source_hash",
+    "expected_revision",
+    "preview_token",
+    "idempotency_key",
+    "confirmed"
+  ],
+  "type": "object"
+}
    • addedInput schema / properties / serp_depth
      Added value: +{
+  "description": "Default number of SERP results to scan per rank check (10, 20, 50, or 100). Omitted keeps the stored depth.",
+  "enum": [
+    10,
+    20,
+    50,
+    100
+  ],
+  "type": "integer"
+}
  2. First observedv0.6.1

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare the mutation/safety profile (readOnly=false, destructive=false, openWorld=false). The description adds substantial behavioral context: never auto-confirm, stale/expired review handling, whole-schedule replacement with field-level reset defaults, and which fields retain stored values when omitted.

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-loads the review/confirm requirement before the update semantics, which is the right priority. It is dense and long at eight sentences, but nearly every sentence carries distinct, non-redundant operational information.

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?

For a 13-parameter mutation with a nested review object and no output schema, the description covers the confirm workflow, reset behavior, and market selection completely enough for an agent to invoke it correctly.

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

Parameters4/5

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

Schema coverage is only 54%, so the description must compensate, and it does so for the most consequential semantics: schedule fields reset to defaults (jitter 60, timezone UTC, no cron) while serp_depth/serp_stop_on_match persist, and country+device vs location_key for the market. It leaves city, raw country/timezone syntax, and the top-level idempotency_key less explained.

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+resource (update project default rank-check schedule, SERP depth, SERP market) and ties the operation to the preview/confirm flow. It clearly distinguishes itself from siblings like preview_project_defaults, get_project_defaults, and search_locations.

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 explains when the review block is required ('Missing review is refused by current servers'), how to recover from a stale preview ('requires a new preview'), and routes to search_locations with the instruction to pass location_key verbatim. It names alternatives and the conditions selecting them.

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