Skip to main content
Glama

governance-platform

by ai.geodesiclabs

update_blueprint

Idempotent

Update an existing Blueprint in place. Only passed fields change; pass [] to clear a list. workflow_name cannot be renamed and existing API keys keep working. Different from create_blueprint: modifies an existing Blueprint, mints no new key.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoNew mode: observe or enforce; omit to keep current
api_keyYesGeodesicAI API key (gai_...)
require_mathNoValidate mathematical relationships
customer_nameNoOrganization or project name (also used for storage folder naming)
workflow_nameYesUnique Blueprint identifier; the value passed as 'blueprint' in validate
derived_fieldsNoField names the platform computes from other fields, e.g. ['subtotal','total']
semantic_checksNoDomain-specific semantic check objects
derivation_rulesNoMath rules as objects. Types: add, subtract, multiply, divide, round, copy, sum (multi-operand), items_multiply, items_sum. Each needs 'type' plus its fields; see the blueprint_guide prompt
extracted_fieldsNoField names the agent extracts from source data, e.g. ['vendor','qty','unit_cost']
require_coherenceNoCheck cross-field plausibility
formal_constraintsNoConstraint objects. Types incl. magnitude_anchor {field,min,max}, relative_anchor {field,reference_field,ratio_min,ratio_max}, max_action_threshold {field,threshold,on_violation}, required_fields {fields}, equals, range, in_set, regex_match, items_magnitude_anchor; see the blueprint_guide prompt
require_provenanceNoRequire extraction source locations for fields
require_consistencyNoCheck internal field consistency
enable_drift_trackingNoTrack pattern stability across batches
require_high_assuranceNoStrictest mode: every check must pass
enable_anomaly_detectionNoFlag records that break no rules but do not fit the reference pattern

TDQS

A4.8/5.0
Behavior5/5

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

Beyond annotations (idempotentHint, non-destructive), the description reveals partial update semantics ('Only passed fields change'), list clearing syntax ('pass [] to clear a list'), immutability of workflow_name, and that existing API keys are unaffected. These are behavioral details not present in the schema or annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, each carrying distinct information. The first states the core operation, the second conveys mutation semantics and constraints, and the third differentiates from create_blueprint. No filler or redundancy.

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?

The tool has 16 parameters and no output schema, but the description covers the essential operational contract: what updates, how partial updates behave, how to clear lists, what cannot change, and side effects on API keys. It omits error cases and return format, but for an update operation with the annotations provided, this is sufficient to invoke 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?

The schema covers 100% of parameters, but the description augments meaning with global update semantics: only passed fields change and [] clears lists. This is especially helpful for array-typed parameters like derived_fields and semantic_checks, though it doesn't map each parameter individually.

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?

The description opens with 'Update an existing Blueprint in place' – a specific verb and resource. It explicitly contrasts with create_blueprint by stating it modifies an existing Blueprint and mints no new key, distinguishing it from the closest sibling.

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?

It names create_blueprint as the alternative and explains the functional difference: 'modifies an existing Blueprint, mints no new key.' It also sets clear expectations by noting workflow_name cannot be renamed and existing API keys keep working, offering both when-to-use and limitation context.

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

All governance-platform toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0
Disambiguation3/5

Most tools have distinct purposes, but several pairs overlap heavily (validate vs validate_repair, repair vs repair_path, analyze_anomaly vs check_drift vs decompose_failure). Detailed descriptions help disambiguate, but the large number of analytics and diagnostics tools creates real selection risk.

Naming Consistency4/5

The vast majority use a consistent snake_case verb_noun pattern (create_blueprint, list_api_keys, verify_certificate). A few single-word or noun-phrase exceptions (validate, forecast, structural_types, recent_inference_decisions) are minor deviations, but overall the pattern is predictable.

Tool Count2/5

At 37 tools, this exceeds the 25+ threshold for 'too many'. While the governance domain is broad, the set could be consolidated (e.g., merging validate_repair into validate, folding repair_path into repair, or trimming diagnostics-tier tools like check_realization and geometric_confidence).

Completeness4/5

The surface covers the full blueprint lifecycle, validation, repair, API key management, discovery, inference governance, and chain management. Minor gaps exist: no direct get_blueprint (only list with counts), and chain lifecycle lacks delete/list/cancel operations. Overall, agents can accomplish core governance tasks without dead ends.

Resources