Recent generation-governance decisions across all runs - what was approved, held, and escalated.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum rows to return | |
| action | No | Optional action filter (STOP, CONTINUE, REVIEW, ...) | |
| api_key | Yes | GeodesicAI API key (gai_...) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, establishing safety. The description adds the scope ('across all runs') and the categories of decisions, but does not disclose ordering, pagination behavior, or how filters interact with the list. With annotations covering safety, this is acceptable but not rich.
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 a single line plus a clarifying fragment, with no redundancy. It is front-loaded with the main purpose and scoped clearly. Every word earns its place.
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 read-only listing tool with full parameter schema coverage and safety annotations, the description is adequate but not complete. It does not describe the output format or any edge cases (e.g., empty results), and there is no output schema to compensate.
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% and parameters (limit, action, api_key) are self-explanatory from their schema descriptions. The tool description does not add any parameter-specific meaning, 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 clearly states the tool returns recent generation-governance decisions across all runs, with specific decision types (approved, held, escalated). It effectively distinguishes from governance actions like govern_inference or approve_rule, though it lacks an explicit verb like 'list' or 'fetch'.
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?
The description provides no guidance on when to use this tool versus alternatives. It does not mention exclusions or contextual use cases, such as 'use this to review past decisions' vs 'use govern_inference to make a new decision'. The 'across all runs' scope is useful but does not constitute usage guidance.
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.
