Reject a discovered candidate rule so it will not be promoted into a Blueprint. Pair with approve_rule after discover_patterns.
| Name | Required | Description | Default |
|---|---|---|---|
| api_key | Yes | GeodesicAI API key (gai_...) | |
| rule_id | Yes | Discovered rule ID from discover_patterns | |
| blueprint | No | Blueprint name (workflow_name) to use | default |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only (false), destructive (false), and idempotent (true). The description adds that the operation prevents promotion into a Blueprint and that it's a follow-up to discover_patterns, enriching the behavioral context without contradicting annotations.
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?
Two sentences with front-loaded action, then consequence and workflow linkage. No redundant words.
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 simple two-required-param action with good schema and annotations, the description provides sufficient context: purpose, effect, and workflow position. It could mention reversibility or return value, but overall it's adequate.
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?
All three parameters have descriptive schema text (100% coverage). The description does not add new parameter meaning beyond the schema, but it's consistent and clarifies the origin of rule_id ('from discover_patterns'), which is already in the schema. Baseline 3 applies.
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 uses a specific verb ('Reject') with a clear resource ('discovered candidate rule') and outcome ('will not be promoted into a Blueprint'). It explicitly references approve_rule and discover_patterns, distinguishing it from sibling 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?
It provides workflow context: 'Pair with approve_rule after discover_patterns' indicates the tool is used in sequence after discovery and as the counterpoint to approval. Though not exhaustive, it clearly situates the tool relative to alternatives.
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.
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.
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.
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).
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.
