Summarize an already-computed state_vector into a confidence level (high/medium/low) with a recommendation. Post-hoc digest - use analyze_anomaly or check_drift for fresh analysis of raw data.
| Name | Required | Description | Default |
|---|---|---|---|
| api_key | Yes | GeodesicAI API key (gai_...) | |
| state_vector | Yes | state_vector object from a prior validate or get_execution_trace result |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds context that this is a post-hoc digest, meaning it does not perform fresh analysis, and that it produces a recommendation. This extra context about the tool's behavior goes beyond the annotations, though it does not disclose error handling or edge cases.
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 two sentences, with the primary purpose in the first sentence and usage guidance in the second. Every word earns its place, and it is front-loaded with the core functionality.
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?
Despite having no output schema, the description clearly states the return value (confidence level with a recommendation) and the input requirement (state_vector from validate or get_execution_trace). Given the tool's simplicity and strong annotations, this is complete and unambiguous.
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?
Schema description coverage is 100%, with both api_key and state_vector having descriptive schema text. The tool description adds no further parameter-level details, so the baseline of 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 ('Summarize') and a precise resource ('an already-computed state_vector') and states the output (a confidence level high/medium/low with a recommendation). It also differentiates from siblings by explicitly mentioning analyze_anomaly and check_drift as alternatives, establishing a clear post-hoc role.
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 explicitly says when to use this tool ('Post-hoc digest') and when not to ('use analyze_anomaly or check_drift for fresh analysis of raw data'). Naming the alternative tools provides clear guidance for selection.
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.
