ba_ground

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

With no annotations provided, the description takes full responsibility for behavioral transparency. It explains the auto-acceptance logic based on fact_kind and anchor resolvability, and mentions idempotency. However, it does not cover potential side effects, error states, or prerequisites like having an active ground session, which would enhance completeness.

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 concise and well-structured, using a bullet-like format to explain the input structure and conditional logic. It packs a lot of information without redundancy, though it could be slightly broken into separate sentences for clarity.

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?

Given the tool's complexity (2 parameters, nested observations, no output schema, no annotations), the description covers the essential behavioral aspects: auto-acceptance criteria, idempotency, and observation classification. It does not describe the return value or explicitly tie to the broader session workflow, but it is largely sufficient for an AI agent to use the tool correctly.

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?

The input schema has 0% description coverage, so the description must add meaning. It effectively explains the semantics of the 'observations' parameter, including the auto-acceptance behavior for different fact_kind values and the role of anchors. However, 'projectRoot' is not described, though its purpose might be inferred.

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's purpose: to record code observations during a ground session. It specifies the input format (fact_kind, claim, anchors) and distinguishes between auto-accepted existence facts and inferred observations, providing a complete understanding of what the tool does.

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 mentions 'ground session only', which implies a specific usage context. However, it does not explicitly state when to use this tool versus its siblings (e.g., ba_assess, ba_impact), nor does it provide guidance on when not to use it. The usage context is implied but not fully elaborated.

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